Former school and college science teacher, teacher educator, research supervisor, and research methods lecturer. Emeritus Professor of Science Education at the University of Cambridge.
Could an oral Covid-19 treatment be available soon?
There was an item on the BBC radio programme/podcast 'Science in Action' (23rd September 2021) about anti-viral agents being used in response to the COVID-19 pandemic: 'Could an oral Covid-19 treatment be available soon?'
"But even after someone is infected, the host actually mounts, for all these [respiratory] viruses, a really dramatic immune and inflammatory response. So it sort of lights a fire. And even when the virus stops replicating, you know that fire continues to burn, and in a lot of cases that's what lands people in the hospital. And so you want to prevent the virus from igniting that fire, that is what really ends up causing a huge amount of damage to the patient. …
the greatest benefit [of the antiviral drug being tested] is in the outpatient setting before that fire gets ignited."
Daria Hazuda being interviewed on 'Science in Action'
A scientific simile
Science communicators, such as teachers, but also scientists and journalists presenting science in the public media, often use techniques to 'make the unfamiliar familiar', to get across abstract or difficult ideas in ways that their audience can relate to.
These techniques can include analogies, metaphors and similes. Here Dr Hazuda used an analogy between the damage to tissue that can occur in disease, and the damage a fire can do. In particular, she was suggesting that the virus may be seen as like something which ignites a fire (such as a match or a spark) but which is not needed to keep the fire going once it had taken hold.
She introduced this idea by suggesting that the virus "sort of lights a fire". This can be considered a simile, which is a figure of speech which is a kind of explicit comparison where one thing is said to be like or similar to another.2 Dr Hazuda did not suggest that the virus actually lights a fire, but rather it has an effect which can be considered somewhat like ('sort of') igniting a fire.
"We didn't start the fire It was always burning, since the world's been turning We didn't start the fire No, we didn't light it, but we tried to fight it"
Billy Joel
Viruses triggering long term disease
The symptoms we experience when ill can be the results of our immune system reacting to illness, rather than the direct effect of the disease causing agent. That does not mean the disease itself would not harm us (infectious agents may be destroying cells which would not be obvious until extensive damage was done), but that in some conditions what we notice – perhaps sneezing, coughing, a raised temperature – is due to the immune response.
The immediate context of the Science in Action interview was the current COVID-19 pandemic caused by infection with the SARS-CoV-2 virus. However, the idea that a viral infection may trigger ('ignite') a longer term immune response (the 'fire') is not new with COVID. The syndrome sometimes known as chronic fatigue syndrome has unknown cause(s), but viruses are among the suspects. Viruses have been suspected as being a possible trigger (if perhaps in combination with other factors) in a range of autoimmune conditions. In autoimmune conditions the mechanisms that usually protect a person from infectious agents such as (some) bacteria and viruses attack and destroy the person's own cells leading to inflammation and potentially serious tissue damage.
People might commonly say that the immune system is 'meant' or 'intended' to protect us from diseases and that it sometimes 'goes wrong' leading to autoimmune disease – but strictly this is not a scientific way of thinking. The immune system has no purpose as such (this would be 'teleological' thinking), but has just evolved in ways such that it has on balance increased fitness.
From that perspective, it might not seem so strange that our immune systems are sometimes insufficient to protect us from harm, and yet can also sometimes be over-sensitive and start doing damage – as that surely is what we might expect if evolution has (through natural selection) led to a system which has tendedon the whole to be protective.
The admirable HLA-B27?
"HLA B27 plays an admirable, perhaps outstanding role in the immune response to viruses, however, it is also directly involved in the pathogenesis of the spondyloarthropathies"
Bowness, 2002: 866
My late wife Philippa was diagnosed with a complex autoimmune condition – she was told that she had atypical Wegener's granulomatosis (a disease now usually called Granulomatosis with polyangiitis2), a form of vasculitis (a disease leading to inflammation in the blood vessels), and that she might have been genetically susceptible to autoimmune diseases because she produced a particular type of human leukocyte antigen, HLA-B27. HLA is an important component of human immune systems, but the precise antigens a person produces varies, depending on their genes (just as we all have blood but people can be assigned into different blood groups). It was also suggested to her that an otherwise minor infection may have acted as a trigger in setting off the autoimmune problems.
Medicine today has some effective agents such as steroids that help 'dampen down' the 'fires' that damage tissues in autoimmune diseases. But these conditions can be very serious. Fifty years ago, most people found to have Wegener's granulomatosis were dead from that damage within a year of their diagnosis.
HLA-B27 is only found in a minority of people in most populations and is associated with a higher prevalence of certain immune conditions such as ankylosing spondylitis (an inflammatory condition especially affecting the spine), inflammatory bowel disease, and some forms of arthritis. It might seem odd that evolution has not led to the elimination of HGLA-B27 if it is associated with serious medical conditions. Yet, again, it may be that something which can make people prone to some conditions may also be better at protecting them from others.
People with HLA-B27 may be better at mounting an effective immune response to some viral infections (the fire is more readily ignited, we might say) and this might be enough of an advantage to balance its unfortunate role in autoimmune conditions. Over human history, HLA-B27 might have protected a great many people from dangerous infections, if also being responsible for a smaller number becoming very ill.
"HLA-B27 appears to excel at its natural function of binding and presenting viral peptide epitopes to cytotoxic T cells. We have suggested that HLA-B27 may, however, act as a 'double-edged sword'. Thus, certain features of its peptide binding ability or cell biology (perhaps those favouring excellent antiviral responses) might also lead to autoimmunity."
McMichael & Bowness, 2002: S157
That is, what makes this immune component so good at attacking certain viruses (as if the immune system had been doused in petrol so that the slightest spark might initiate a response) may also be responsible for its association with autoimmune diseases. HLA-B27 may (metaphorically) be the can of petrol that means that a viral spark starts not just a fire, but a conflagration.
1: "the first oral, direct-acting antiviral shown to be highly effective at reducing nasopharyngeal SARS-CoV-2 infectious virus" according to a preprint reported at medRχiv). A preprint is a paper written to report scientific research but NOT yet tested through peer review and formally published, and so treated as reporting more provisional and uncertain findings than a peer-reviewed paper.
2 By comparison, a metaphor may be considered an implicit comparison presented as if an identity: e.g., the nucleus is the brain of the cell.
2. The disease was named after the German physician Friedrich Wegener who described the condition. After Wegener was identified as a Nazi and likely war criminal (suspected, but not convicted) it was decided to rename the disease.
When I was listening to the radio news I heard a clip of the Rt. Hon. Sajid Javid MP, the U.K. Secretary of State for Health and Social Care, talking about the ongoing response to the COVID pandemic:
Health Secretary Sajid Javid talking on 12th September
"Now that we are entering Autumn and Winter, something that COVID and other viruses, you know, usually like, the prime minister this week will be getting out our plans to manage COVID over the coming few months."
Sajid Javid
So, COVID and other viruses usually like Autumn and Winter (by implication, presumably, in comparison with Spring and Summer).
This got me wondering how we (or Sajid, at least) could know what the COVID virus (i.e., SARS-CoV-2 – severe acute respiratory syndrome coronavirus 2) prefers – what the virus 'likes'. I noticed that Mr Javid offered a modal qualification to his claim: usually. It seemed 'COVID and other viruses' did not always like Autumn and Winter, but usually did.
Yet there was a potential ambiguity here depending how one parsed the claim. Was he suggesting that
[COVID and other viruses]
usually
like Autumn and Winter
or
COVID
[and other viruses usually]
like Autumn and Winter
This might have been clearer in a written text as either
COVID and other viruses usually like Autumn and Winter
or
COVID, and other viruses usually, like Autumn and Winter
The second option may seem a little awkward in its phrasing, 1 but then not all viral diseases are more common in the Winter months, and some are considered to be due to 'Summer viruses':
"Adenovirus, human bocavirus (HBoV), parainfluenza virus (PIV), human metapneumovirus (hMPV), and rhinovirus can be detected throughout the year (all-year viruses). Seasonal patterns of PIV are type specific. Epidemics of PIV type 1 (PIV1) and PIV type 3 (PIV3) peak in the fall [Autumn] and spring-summer, respectively. The prevalence of some non-rhinovirus enteroviruses increases in summer (summer viruses)"
Moriyama, Hugentobler & Iwasaki, 2020: 86
Just a couple of days later Mr Javid was being interviewed on the radio, and he made a more limited claim:
Health Secretary Sajid Javid talking on BBC Radio 4's 'Today' programme, 15th September
"…because we know Autumn and Winter, your COVID is going to like that time of year"
Sajid Javid
So, this claim was just about the COVID virus, not viruses more generally, and that we knowthat COVID is going to like Autumn and Winter. No ambiguity there. But how do we know?
Coming to knowledge
Historically there have been various ways of obtaining knowledge.
Divine revelation: where God reveals the knowledge to someone, perhaps through appearing to the chosen one in a dream.
Consulting an oracle, or a prophet or some other kind of seer.
Intuiting the truth by reflecting on the nature of things using the rational power of the human intellect.
Empirical investigation of natural phenomena.
My focus in this blog is related to science, and given that we are talking about public health policy in modern Britain, I would like to think Mr Javid was basing his claim on the latter option. Of course, even empirical methods depend upon some metaphysical assumptions. For example, if one assumes the cosmos has inbuilt connections one might look for evidence in terms of sympathies or correspondences. Perhaps, if the COVID virus was observed closely and looked like a snowflake, that could (in this mindset) be taken as a sign that it liked Winter.
A snowflake – or is it a virus particle? (Image by Gerd Altmann from Pixabay)
Sympathetic magic
This kind of correspondence, a connection indicated by appearance, was once widely accepted, so that a plant which was thought to resemble some part of the anatomy might be assumed to be an appropriate medicine for diseases or disorders associated with that part of the body.
This is a kind of magic, and might seem a 'primitive' belief to many people today, but such an idea was sensible enough in the context of a common set of underlying beliefs about the nature and purposes of the world, and the place and role of people in that world. One might expect that specific beliefs would soon die out if, for example, the plant shaped like an ear turned out to do nothing for ear ache. Yet, at a time when medical practitioners could offer little effective treatment, and being sent to a hospital was likely to reduce life expectancy, herbal remedies at least often (if not always) did no harm.
Moreover, many herbs do have medicinal properties, and something with a general systemic effect might work as topical medicine (i.e., when applied to a specific site of disease). Add to that, the human susceptibility to confirmation bias (taking more notice of, and giving more weight to, instances that meet our expectations than those which do not) and the placebo effect (where believing we are taking effective medication can sometimes in itself have beneficial effects) and the psychological support offered by spending time with an attentive practitioner with a good 'bedside' manner – and we can easily see how beliefs about treatments may survive limited definitive evidence of effectiveness.
The gold standard of experimental method
Of course, today, we have the means to test such medicines by taking a large representative sample of a population (of ear ache sufferers, or whatever), randomly dividing them into two groups, and using a double-blind (or should that be double-deaf) approach, treat them with the possible medicine or a placebo, without either the patient or the practitioner knowing who was getting which treatment. (The researchers have a way to know of course – or it would difficult to deduce anything from the results.) That is, the randomised control trial (RCT).
Now, I have been very critical of the notion that these kinds of randomised experimental designs should be automatically be seen as the preferred way of testing educational innovations (Taber, 2019) – but in situations where control of variables and 'blinding' is possible, and where randomisation can be applied to samples of well-defined populations, this does deserve to be considered the gold standard. (It is when the assumptions behind a research methodology do not apply that we should have reservations about using it as a strategy for enquiry.)
So can the RCT approach be used to find out if COVID has a preference for certain times of year? I guess this depends on our conceptual framework for the research (e.g., how do we understand what a 'like' actually is) and the theoretical perspective we adopt.
So, for example, behaviourists would suggest that it is not useful to investigate what is going on in someone's mind (perhaps some behaviorists do not even think the mind concept corresponds to anything real) so we should observe behaviours that allow us to make inferences. This has to be done with care. Someone who buys and eats lots of chocolate presumably likes chocolate, and someone who buys and listens to a lot of reggae probably likes reggae, but a person who cries regularly, or someone that stumbles around and has frequent falls, does not necessary like crying, or falling over, respectively.
A viral choice chamber
So, we might think that woodlice prefer damp conditions because we have put a large number of woodlice in choice chambers with different conditions (dry and light, dry and dark, damp and light, damp and dark) and found that there was a statistically significant excess of woodlice settling down in the damp sections of the chamber.
Of course, to infer preferences from behaviour – or even to use the term 'behaviour' – for some kinds of entity is questionable. (To think that woodlice make a choice based on what they 'like' might seem to assume a level of awareness that they perhaps lack?) In a cathode ray tube electrons subject to a magnetic field may be observed (indirectly!) to move to one side of the tube, just as woodlice might congregate in one chamber, but I am not sure I would describe this as electrons liking that part of the tube. I think it can be better explained with concepts such as electrical charge, fields, forces, and momentum.
It is difficult to see how we can do double blind trials to see which season a virus might like, as if the COVID virus really does like Winter, it must surely have a way of knowing when it is Winter (making blinding impossible). In any case, a choice chamber with different sections at different times of the year would require some kind of time portal installed between its sections.
Like electrons, but unlike woodlice, COVID viral particles do not have an active form of transport available to them. Rather, they tend to be sneezed and coughed around and then subject to the breeze, or deposited by contact with surfaces. So I am not sure that observing virus 'behaviour' helps here.
So perhaps a different methodology might be more sensible.
A viral opinion poll
A common approach to find out what people like would be a survey. Surveys can sometimes attract responses from large numbers of respondents, which may seem to give us confidence that they offer authentic accounts of widespread views. However, sample size is perhaps less important than sample representativeness. Imagine carrying out a survey of people's favourite football teams at a game at Stamford Bridge; or undertaking a survey of people's favourite bands as people queued to enter a King Crimson concert! The responses may [sic, almost certainly would] not fully reflect the wider population due to the likely bias in such samples. Would these surveys give reliable results which could be replicated if repeated at the Santiago Bernabeu or at a Marillion concert?
How do we know what 'COVID 'really likes? (Original Images by OpenClipart-Vectors and Gordon Johnson from Pixabay)
A representative sample of vairants?
This might cause problems with the COVID-19 virus (SARS-CoV-2). What counts as a member of the population – perhaps a viable virus particle? Can we even know how big the population actually is at the time of our survey? The virus is infecting new cells, leading to new virus particles being produced all the time, just as shed particles become non-viable all the time. So we have no reliable knowledge of population numbers.
Moreover, a survey needs a representative sample: do the numbers of people in a sample of a human population reflect the wider population in relevant terms (be that age, gender, level of educational qualifications, earnings, etc.)? There are viral variants leading to COVID-19 infection – and quite a few of them. That is, SARS-CoV-2 is a class with various subgroups. The variants replicate to different extents under particular conditions, and new variants appear from time to time.
So, the population profile is changing rapidly. In recent months in the UK nearly all infections where the variant has been determined are due to the variant VOC-21APR-02 (or B.1.617.2 or Delta) but many people will be infected asymptotically or with mild symptoms and not be tested, and so this likely does not mean that VOC-21APR-02 dominates the SARS-CoV-2 population as a whole to the extent it currently dominates in investigated cases. Assuming otherwise would be like gauging public opinion from the views of those particular people who make themselves salient by attending a protest, e.g.:
"Shock finding – 98% of the population would like to abolish the nuclear arsenal,
according to a [hypothetical] survey taken at the recent Campaign for Nuclear Disarmament march"
In any case, surveys are often fairly blunt instruments as they need to present objectively the same questions to all respondents, and elicit responses in a format that can be readily classified into a discrete number of categories. This is why many questionnaires use Likert type items:
Would you say you like Autumn and Winter:
1
2
3
4
5
Always
Nearly always
Usually
Sometimes
Never
Such 'objective' measures are often considered to avoid the subjective nature of some other types of research. It may seem that responses do not need to be interpreted – but of course this assumes that the researchers and all the respondents understand language the same way (what exactly counts as Autumn and Winter? What does 'like' mean? How is 'usually' understood – 60-80% of the time, or 51-90% of the time or…). We can usually (sic) safely assume that those with strong language competence will have somewhat similar understandings of terms, but we cannot know precisely what survey participants meant by their responses or to what extent they share a meaning for 'usually'.
There are so-called 'qualitative surveys' which eschew this kind of objectivity to get more in-depth engagement with participants. They will usually use interviews where the researcher can establish rapport with respondents and ask them about their thoughts and feelings, observe non-verbal signals such as facial expressions and gestures, and use follow-up questions… However, the greater insight into individuals comes at a cost of smaller samples as these kinds of methods are more resource-intensive.
But perhaps Mr Javid does not actually mean that COVID likes Autumn and Winter?
So, how did the Department of Health & Social Care, or the Health Secretary's scientific advisors, find out that COVID (or the COVID virus) likes Autumn and Winter? The virus does not think, or feel, and it does not have preferences in the way we do. It does not perceive hot or cold, and it does not have a sense of time passing, or of the seasons.2 COVID does not like or dislike anything.
Mr Javid needs to make himself clear to a broad public audience, so he has to avoid too much technical jargon. It is not easy to pitch a presentation for such an audience and be pithy, accurate, and engaging, but it is easy for someone (such as me) to be critical when not having to face this challenge. Cabinet ministers, unlike science teachers, cannot be expected to have skills in communicating complex and abstract scientific ideas in simplified and accessible forms that remain authentic to the science.
It is easy and perhaps convenient to use anthropomorphic language to talk about the virus, and this will likely make the topic seem accessible to listeners, but it is less clear what is actually meant by a virus liking a certain time of year. In teaching the use of anthropomorphic language can be engaging, but it can also come to stand in place of scientific understanding when anthropomorphic statements are simply accepted uncritically at face value. For example, if the science teacher suggests "the atom wants a full shell of electrons" then we should not be surprised that students may think this is a scientific explanation, and that atoms do want to fill their shells. (They do not of course. 3)
Image by Gordon Johnson from Pixabay
Of course Mr Javid's statements cannot be taken as a literal claim about what the virus likes – my point in this posting is to provoke the question of what this might be intended to mean? This is surely intended metaphorically (at least if Mr Javid had thought about his claim critically): perhaps that there is higher incidence of infection or serious illness caused by the COVID virus in the Winter. But by that logic, I guess turkeys really would vote for Christmas (or Thanksgiving) after all.
Typically, some viruses cause more infection in the Winter when people are more likely to mix indoors and when buildings and transport are not well ventilated (both factors being addressed in public health measures and advice in regard to COVID-19). Perhaps 'likes' here simply means that the conditions associated with a higher frequency/population of virus particles occur in Autumn and Winter?
A snowflake. The conditions suitable for a higher frequency of snowflakes are more common in Winter. So do snowflakes also 'like' Winter? (Image by Gerd Altmann from Pixabay)
However, this is some way from assigning 'likes' to the virus. After all, in evolutionary terms, a virus might 'prefer', so to speak, to only be transmitted asymptomatically, as it cannot be in the virus's 'interests', so to speak, to encourage a public health response that will lead to vaccines or measures to limit the mixing of people.
If COVID could like anything (and of course it cannot), I would suggest it would like to go 'under the radar' (another metaphor) and be endemic in a population that was not concerned about it (perhaps doing so little harm it is not even noticed, such that people do not change their behaviours). It would then only 'prefer' a Season to the extent that that time of year brings conditions which allow it to go about its life cycle without attracting attention – from Mr Javid or anyone else.
The health secretary was interviewed on 1st December
"…we have always known that when it gets darker, it gets colder, the virus likes that, the flu virus likes that and we should not forget that's still lurking around as well…"
Rt. Hon. Sajid Javid MP, the U.K. Secretary of State for Health and Social Care, interviewed on BBC Radio 4 Today programme, 1st December, 2021
Works cited:
Moriyama, M., Hugentobler, W. J., & Iwasaki, A. (2020). Seasonality of Respiratory Viral Infections. Annual Review of Virology, 7(1), 83-101. doi:10.1146/annurev-virology-012420-022445
1. It would also seem to be a generalisation based on the only two Winters that the COVID-19 virus had 'experienced'
2. Strictly I cannot know what it is like to be a virus particle. But a lot of well-established and strongly evidenced scientific principles would be challenged if a virus particle is sentient.
This was a very informative discussion of aspects of statistics, and one of the questions addressed was:
How often do false positive and false negative test results occur in medical screenings?
Screening for disease
Screening programmes test apparently healthy members of the population for serious medical issues in order to catch problems at an early stage when treatment offers the best prognosis.
Screening programmes can quickly test many people… (Image by Ahmad Ardity from Pixabay)
No tests are perfect, so tests will sometimes give misleading results – called false positives and false negatives.
a test result that is:
when an ideal perfect test would have shown positive
when an ideal perfect test would have shown negative
positive
is called a true positive
is called a false positive
negative
is called a false negative
is called a true negative
…but definitive diagnoses may require more sophisticated follow-up investigation (Image by Michal Jarmoluk from Pixabay)
Sometimes tests can be tuned to avoid many false negatives by tolerating a higher rate of false positive (or vice versa). This is similar to what happens in statistical hypothesis testing when the choice of 'confidence level' (the p {for probability} value used as a cut-off criterion for 'statistical significance') can be chosen according to whether it is more important to avoid false positives or to avoid false negatives.
Choice of confidence level reflects a balance between admitting false positives (due to chance events) and false negatives (where real effects are not distinguished from chance events). After, Taber, 2019, Fig. 7.
The notion of 'beyond reasonable doubt' used in criminal trials can be understood as based on the principle that it is better that some guilty perpetrators are not convicted at trial than to risk miscarriages of justice where innocent people may lose their liberty (or indeed in some jurisdictions, perhaps their lives). That is, it is better to have false negatives than false positives in criminal convictions.
In medical screening programmes, it is common to have an initial test which might give quite a few positive results (but hopefully not produce many false negatives, where a person with a disease appears to be clear according to the test), even though most of the positive results will prove to be false alarms (false positives) when followed up by a more sophisticated test that it is impractical or too expensive to use for mass screening.
The bias towards false positives built into some medical screening trials means that a person should not be too despondent at getting a positive result in the initial screen. Dr Yates worked through one example to show that based on the rates of false positives on certain screening tests, a person called for regular screenings over a number of years was actually more likely than not to get at least one positive screening result – but still unlikely to be unlucky enough to have the disease.
A teaching analogy
What I most liked was the use of an analogy to compare the logic of the screening process with a familiar everyday situation. Teaching can be seen as a process of making the unfamiliar familiar, and teachers often do this by comparing the unfamiliar they are charged with teaching about with something already familiar to the their students. That is only a starting point for supporting a developing understanding of the new concept or phenomenon, but it often is very useful in making abstract new ideas seem less threatening or inaccessible.
One common way of making the unfamiliar familiar is through analogy: showing that what is new has a familiar conceptual structure – mapping onto a set of ideas already understood.
Scientists charged with giving talks to a public audience as part of 'public communication' of science ('outreach') or attempts to improve 'public understanding' of science also have the job of making the unfamiliar familiar and may also use teaching analogies – as Dr Yates did here:
"I would make the analogy to screenings with a job interview. So, when a company wants to hire someone for a job, they send out an advert, and people send in their c.v.s. And the company can read those c.v.s quickly and make a shortlist. And that's a really cheap way, just as the first screen is a really cheap way of identifying people, who might be suitable for the job, people who might have breast cancer. And then for the job interview you call people in and you interview them and you throw 'assessment centres' at them, you do tests which are too expensive to do to the whole population at large to identify someone good for the job, but you can do it to this smaller population. And in the same way, with the screen we invite people in and we throw more expensive, more accurate tests at them to give them a diagnosis. And the point is, just because you would get invited to an interview for a job you had applied for, you wouldn't assume that you had got the job, right? So, in the same way, just because you get invited for further tests after a screen, you shouldn't assume you have the disease that is being screened for. You should wait and go to the follow-up test and see what that follow-up test says."
Dr Kit Yates explaining the logic of screening programmes
Based on an analogy used by Dr Kit Yates
This seemed a well-considered analogue, one that would be very accessible to most people in the audience. It is a common experience to have applied for jobs: perhaps sometimes not being shortlisted; sometimes called in for interview but not appointed; and sometimes being offered the job. 2
The explanations flowed nicely between the target concept (screening) and the analogue (shortlisting) – as can be seen in the tabulated version below.
"I would make the analogy to screenings
with a job interview.
So, when a company wants to hire someone for a job, they send out an advert, and people send in their c.v.s.
And the company can read those c.v.s quickly and make a shortlist.
And that's a really cheap way,
just as the first screen is a really cheap way of identifying people,
who might be suitable for the job,
people who might have breast cancer.
And then for the job interview you call people in and you interview them and you throw 'assessment centres' at them, you do tests which are too expensive to do to the whole population at large to identify someone good for the job, but you can do it to this smaller population.
And in the same way, with the screen we invite people in and we throw more expensive, more accurate tests at them to give them a diagnosis.
And the point is, just because you would get invited to an interview for a job you had applied for, you wouldn't assume that you had got the job, right?
So, in the same way, just because you get invited for further tests after a screen, you shouldn't assume you have the disease that is being screened for.
You should wait and go to the follow-up test and see what that follow-up test says."
An effective teaching analogy needs to have an analogue that is sufficiently familiar for an audience to appreciate its conceptual structure – and that structure must fit well when mapped across to the target concept. 'Medical screening is like job shortlisting' seems to work well on both these criteria.
1: "If you see a newspaper headline with a big, bold statistic, how do you know that you can trust it? How often do false positive and false negative test results occur in medical screenings? And how do you safely bet whether or not 2 people in any room will share a birthday? This month we hear from Kit Yates about the maths of medicine, crime and the media, exploring real-world data from his book, 'The Maths of Life and Death'. This talk was recorded from our theatre at the Royal Institution, on 21 January 2020." https://soundcloud.com/royal-institution/maths-trust
2. It might be suggested that this process reflects a middle class /professional/white collar employment experiences, whereas for many jobs, such as much shop or factory work, an employer is likely to employ the first apparently suitable candidate that applies, rather than using a slower and more expensive two stage process. This is so, but the situation of short-listing is still generally familiar through story lines in fiction, such as in television dramas.
Is your shampoo of natural, unnatural, or supernatural origin?
Keith S. Taber
It seems that some of the ingredients of a well-known brand of hair care products are not of natural origin (Image by Stefan Keller from Pixabay)
A well know brand of hair products is being advertised on television with an explicit claim that the shampoo is 94% of natural origin. Clearly there is also an implicit claim here about the other 6%! This dubious claim does not seem to be a slip of the tongue, as similar references can be found in product details on line (including the examples below). The science teacher in me knew that it was this kind of nonsense which supports common misconceptions about 'natural' being inherently good, and there being a clear distinction between materials that are 'natural', and those that are not.
Shampoos from brands other than Herbal Essences are 100% of natural origin.
The other evening I was watching television, and there was a shampoo being advertised, and although I was not paying attention I thought I heard the claim that the shampoo contained products of 94% natural origin. Had I misheard – a quick 'rewind' suggested not.
My next assumption was that this was sloppy language being used by some advertising copywriter, and that the manufacturer who commissioned the commercial simply had not noticed the slip. So I had a look on line.1 It seems that the brand concerned, Herbal Essences, has a habit or topping up its products with material that is not of natural origin. The company claims it is using at least 90% materials of natural original in its latest products (see the examples below), and this is apparently seen as a positive point to stress in its marketing.
But this is just nonsense. If the shampoo was fabricated using 94% products of natural original, then 6% was not of natural origin. This leaves me to wonder where the rest originates. A shampoo, any shampoo, is 100% of natural origin.
Natural products chemistry
In chemistry there is a common term natural products which tends to be used for materials extracted from living organisms – one can extract vitamin C from oranges, and insulin for diabetics used to be extracted from pancreases from farm animals (although now it is produced by the activities of bacteria or yeast). In that sense salt (produced by evaporating sea water) and chalk (deriving from the shells debris from long dead sea organisms) are not natural products. But like everything else in the material world, salt and chalk are still of natural origin.
So what is a hair product which is not of natural origin, or which is only partially of natural origin? It seems there are two obvious contrasts to natural, which are 'unnatural' and 'supernatural'. Presumably the company was not suggesting it used ingredients of supernatural origin?
Do Herbal Essences employ a specialist formulation technologist to prepare the shampoo ingredients that are not of natural origin? (Image by pendleburyannette from Pixabay)
What makes something unnatural?
Assuming Herbal Essences products do not include material of supernatural origin, the other option would seem to be material of unnatural origin. But what makes a material unnatural.
At various times, in various cultural contexts, the divine right of kings, feudalism and slavery will have been seen as perfectly natural, as well the subservience of women to men. Certain sexual acts that are now widely (if not universally) considered part of the normal range of human behaviours have at various times in different societies been considered unnatural – indeed so unnatural that those found to have 'committed' them might be put to death.
Given that the question of 'what is human nature?' is not settled (didn't Immanuel Kant think this was the core task for philosophy?) the approach that is sometimes taken is to look instead to 'nature' herself (for nature is a 'she' as has long been established – in part justifying her domination and mistreatment by 'man'). If it happens in nature, then that's natural.
"The sun rises everyday but animals occasionally give birth to monsters. 'Natural is what occurs always or almost always', says Aristotle, generalizing from this experience."
Paul Feyerabend
So, by this criterion, saving lives with blood transfusions is not natural, and nor is hip replacement surgery, nor using an incubator to stop premature babies dying. However, cancer is natural. Pushing your siblings out of the nest, or pecking them to death, to get a greater share of the food your parents bring home is perfectly natural. Depositing your eggs in another creature, and paralysing it so that it acts as a defenseless (but alive, and so fresh) source of food when your offspring hatch out inside it, is natural.
"We can save you if you wish, but only by unnatural acts" (Image by Mohamed Hassan from Pixabay)
The man-made is not 'natural'
This depends upon demarcating humans as somehow outside of nature. This is difficult for a natural scientist to accept as 'ever since Darwin' (to borrow a phrase) it has been difficult to see how humans can be considered inherently distinct from the rest of the natural world, even if contingency has led to some obvious differences in terms of the development of culture. This argument then distinguishes the natural from the synthetic, the man-made.
A space rocket is not natural (in this sense) as it only exists because humans built it. Whether this is qualitatively different from technology elsewhere in nature – a badger's dam, a termite's nest, a honeycomb – rather than just a matter of a (admittedly impressive) difference of degree is an interesting question.
There are no doubt times where it is useful to distinguish between materials and objects that can be collected or extracted form 'natural' sources, and those that only exist because they have been synthesised by people – even if we do need to be wary of reading too much into the distinction. The Saturn V rocket did not exist 'in nature', and nor does a lemon coated in a wax so that it will stay 'fresh' longer – but one is the product of considerably less processing than the other. 2
Fluorine compounds (fluorides) are added to drinking water in many places to help protect teeth, but in other places the water supply already (i.e., 'naturally') contains fluoride at much higher levels – indeed, sometimes high enough to be considered a medical risk. This both reminds us that what is natural is somewhat arbitrary, and that what is considered natural is not necessarily desirable.
Natural and natural origin
The Saturn V rocket was synthetic – it was not found 'as is', growing in a swamp or being ejected from a volcano ('You Only Live Twice' style). But the materials it was made from were all of natural origin, even if some of them may have been the result of considerable processing of naturally occurring materials.
Everything you see here is of natural origin (From 'You Only Live Twice', Eon Productions)
Any material thing in our world is of natural origin. Some materials are used much as found 'in nature', sometimes some cleaning or tidying is needed (think of natural diamonds being 'cut' to best reflect light), some purifying (separating compounds from crude oil fractions), some extracting (metal from ore), some synthesising (ammonia from hydrogen and nitrogen)… The amount of processing may vary considerably, but everything material that goes into a manufactured product is ultimately of natural origin.
So Herbal Essences products are 100% of natural origin, just as are the products of all their competitors.
A vague distinction
Webpages advertising specific Herbal Essences product lines often simply report that they are of 9n% natural origin, as in the examples below (95%, 96%, 97%). However, I found a page where it was clarified that the 90+% of natural origin included "purified water and ingredient materials derived from a natural source and subjected to limited processing".
So Herbal Essences do not use natural ditch water, or natural swamp water, or even natural sea water in their products, but rather purified water. I am pleased – as I have used Herbal Essences products, and will likely do so again, and I would rather not use dirty water when I am seeking to clean my hair.
Water – easily sourced from nature, and used in hair products (Image by mac231 from Pixabay)
So, it seems that for Herbal Essences, being of natural origin actually means, natural materials found in a suitable form to be used directly, or ("natural derived") only needing a "limited" amount of processing. Limited processing is a good thing in 'green chemistry' terms (less waste, less energy needed) but it is both a vague notion (who is to decide what makes the processing 'limited', and how does a consumer know what Herbal Essences count as limited?), and of course it is simply a quite different concept to being of natural origin.
I guess the company wanted a way of saying they were basing their products on natural products (such as plant extracts) without being misleading by implying that they could simply go and collect all the component materials and use them without needing any further processing. These materials may be pressed, steamed, or separated and purified in other ways, but are not generally the outcomes of complex synthetic processes. I can see both why that would be attractive to consumers, and why it is not easy to get across in a simple catchy term.
Yet the claim that 94% of your hair product is of natural origin, when a moment's thought should lead to the consumer realising that actually all products are of 100% natural origin, is a claim that (unlike the missing 6% of your Herbal Essences brand shampoo), does not have any substance.
a "limited" amount of processing
is both a vague notion and simply a quite different concept to
being of natural origin.
Appendix: Some examples of products that are not completely of natural origin
95% natural origin
The Herbal EssencesCoconut Milk conditioner is, according to their website,
95% natural origin 73% purified water and 22% natural derived ingredients other 5% for a good usage experience & product stability.
"Fruit waxing is the process of covering fruits (and, in some cases, vegetables) with artificial [sic] waxing material. Natural [sic] wax is removed first, usually by washing, followed by a coating of a biological or petroleum derived wax. Potentially allergenic proteins (peanut, soy, dairy, wheat) may be combined with shellac."
The loneliness experiment, a.k.a. The BBC Loneliness Experiment was a study publicised through the BBC (British public service broadcaster), and in particular through it's radio programme All in the Mind, ("which covers psychology, neuroscience & mental health" according to presenter, Claudia Hammond's website.)1 It was launched back in February 2018 – pre-COVD.2
"All in the Mind: The Loneliness Experiment launches the world's largest ever survey of its kind on loneliness." https://www.bbc.co.uk/programmes/b09r6fvn
Claudia Hammond describes herself as an "award-winning broadcaster, author and psychology lecturer". In particular "She is Visiting Professor of the Public Understanding of Psychology at the University of Sussex" where according to the University of Sussex "the post has been specially created for Claudia, who studied applied psychology at the University in the 1990s", so she is very well qualified for her presenting role. (I think she is very good at this role: she has a good voice for the radio and manages to balance the dual role of being expert enough to exude authority, whilst knowing how to ask necessarily naive questions of guests on behalf of non-specialist listeners.)
Loneliness is a serious matter that affects many people, and is not be made light of. So this was a serious study, on an important topic – yet every time I heard this mentioned on the radio (and it was publicised a good deal at the time) I felt myself mentally (and sometimes physically) cringe. Even without hearing precise details of the research design, I could tell this was simply not a good experiment.
This was not due to any great insight on my behalf, but was obvious from the way the work was being described. Readers may wish to see if they can spot for themselves what so irked me.
What is the problem with this research design?
This is how the BBC described the study at its launch:
The Loneliness Experiment, devised by Professor Pamela Qualter and colleagues, aims to look at causes and possible solutions to loneliness. And we want as many people as possible to fill in our survey, even if they've never felt lonely, because we want to know what stops people feeling lonely, so that more of us can feel connected.
This is how Prof. Hammond described the research in retrospect:
55,000 people from around the world chose to take part in the BBC Loneliness Experiment, making it the world's largest ever study on loneliness. Researchers from the universities of Manchester, Brunel and Exeter, led by Professor Pamela Qualter and funded by the Wellcome Trust, developed a questionnaire asking people what they thought loneliness was, when they felt lonely and for how long.
And this is how the work is described on the University of Manchester's pages:
The Loneliness Experiment was a study conducted by BBC Radio 4's All in the Mind….
The study asked respondents to give their opinions and record their experiences of loneliness and related topics, including friendship, relationships, and the use of technology – as well as recording lifestyle and background information. Respondents also engaged in a number of experiments.
The survey was developed by Professor Pamela Qualter, from The University of Manchester's Manchester Institute of Education (MIE), with colleagues from Brunel University London, and the University of Exeter. The work was funded by a grant from The Wellcome Trust.
These descriptions make it obvious that the The Loneliness Experiment was not an experiment. Experiment is a specific kind of research – a methodology where the researchers randomly assign participants randomly to conditions, intervene in the experimental condition,and take measurements to see what effect the intervention has by comparing with measurements in a control condition. True experiments are extremely difficult to do in the social sciences (Taber, 2019), and often quasi-experiments or natural experiments are used which do not meet all the expectations for true experiments. BUT, to be an experiment there has to be something that can be measured as changing over time in relation to specified different conditions.
Experiment involves intervention (Image by Gerd Altmann from Pixabay)
Experiment is not the only methodology used in research – there are also case studies, there is action research and grounded theory, for example – and non-experimental research may be entirely appropriate in certain situations, and can be of very high quality. One alternative methodology is the survey which collects data form a sample of a population at some particular time. Although surveys can be carried out in various ways (for example, through a series of observations), especially common in social science is the survey (a methodology) carried out by using participant self-responses to a questionnaire (a research instrument).
it is clear from the descriptions given by the BBC, Professor Hammond and the University of Manchester that the The Loneliness Experiment was not actually an experiment at all, but basically a survey (even if, tantalisingly, the Manchester website suggests that "Respondents also [sic] engaged in a number of experiments". )
The answer to the question 'when is an experiment not an experiment?' might simply be: when it is something other than an experiment
Completing a questionnaire (Image by Andreas Breitling from Pixabay)
What's in a name: does it really matter?
Okay, so I am being pedantic again.
But I do think this matters.
I think it is safe to assume that Prof. Hammond, Prof. Qualter and colleagues know the difference between an experiment and a survey. Presumably someone decided that labelling the research as the loneliness study or the loneliness survey would not be accessible (or perhaps not as impressive) to a general audience and so decided to incorrectly use the label experiment as if experiment was synonymous with study/research.
As a former research methods lecturer, that clearly irks as part of my job was to teach new researchers about key research concepts. But I would hope that people actually doing research or learning to do research are not going to be confused by this mislabelling.
But, as a former school science teacher, I know that there is widespread public misunderstanding of key nature of science terms such as theory and experiment. School age students do need to learn what is meant by the word experiment, and what counts as an experiment, and the BBC is being unhelpful in presenting research that is not experimental as an experiment – as this will simply reinforce common misconceptions of what the term experiment is actually used to denote in research .
So, in summary, I'll score The BBC Loneliness Experiment
2: It would have been interesting to repeat when so many people around the world were in 'lock-down'. (A comparison between pre-COVID and pandemic conditions might have offered something of a natural experiment.)
Bee-ware chemicals! (Images by PollyDot and Clker-Free-Vector-Images from Pixabay)
A recent episode of the BBC Inside science radio programme and podcast was entitled 'Bees and multiple pesticide exposure'. This discussed a very important issue that I have no wish to make light of. Researchers were looking at the stressors which might be harming honey bees, very important pollinators for many plants, and concluded that these likely act synergistically. That is a colony suffering from, say a drought and at the same time a mite infection, will show more damage that one would expect from simply adding the typical harm of each as if independent effects. Rather there are interactions.
This is hardly surprising, but is none-the-less a worrying finding.
Bees and multiple pesticide exposure episode of BBC Inside Science
However, my 'science teacher' radar honed in on an aspect of the language used to explain the research. The researcher interviewed was Dr Harry Siviter of the University of Texas at Austin. As part of his presentation he suggested that…
"Exposure to multiple pesticides is the norm, not the exception. So, for example a study in North America showed that the average number of chemicals found in a honey bee colony is six, with a high of 42. So, we know that bees are exposed to multiple chemicals…"
The phrase that stood out for me was "the average number of chemicals found in a honey bee colony is six" as clearly that did not make any sense scientifically. At least, not if the term 'chemical' was meant to refer to 'chemical substance'. I cannot claim to know just how many different substances would be found if one analysed honey bee colonies, but I am pretty confident the average would be orders of magnitude greater than six. An organism such as a bee (leaving aside for a moment the hive in which it lives) will be, chemically, 'made up' of a great many different proteins, amino acids, lipids, sugars, nuclei acids, and so forth.
"the average number of chemicals found in a honey bee colony is six"
From the context, I understood that Dr Siviter was not really talking about chemicals in general, but pesticides. So, I am (not for the first time) being a pedant in pointing out that technically he was wrong to suggest "the average number of chemicals found in a honey bee colony is six" as any suitably informed listener would have immediately, and unproblematically, understood what he meant by 'chemicals' in this context.
Yet, as a teacher, my instinct is to consider that programmes such as this, designed to inform the public about science, are not only heard by those who are already well-versed in the sciences. By its nature, BBC Inside Science is intended to engage with a broad audience, and has a role in educating the public about science. I also knew that this particular pedantic point linked to a genuine issue in science teaching.
A common alternative conception
The term chemical is not usually used in science discourse as such, but rather the term substance. Chemical substances are ubiquitous, although in most everyday contexts we do not come across many pure samples of single substances. Tap water is nearly all water, and table salt is usually about 99% sodium chloride, and sometimes metals such as copper or aluminium are used in more or less pure form. But these tend to be exceptions – most material entities we engage with are not pure substances ('chemicals'), rather being mixtures or even more complex (e.g., wood or carrot or hair).
In everyday life, the term chemical tends to be used more loosely – so, for example, household bleach may be considered 'a chemical'. More problematically 'chemicals' tends to be seen as hazardous, and often even poisonous. So, people object to there being 'chemicals' in their food – when of course their food comprises chemicals and we eat food to access those chemicals because we are also made up of a great many chemicals. Food with the chemicals removed is not food, or indeed, anything at all!
In everyday discourse 'chemical' is often associated with 'dangerous' (Image by Arek Socha from Pixabay)
So, science teachers not only have the problem that in everyday discourse the term 'chemical' does not map unproblematically on 'substance' (as it is often used also for mixtures), but even more seriously that chemicals are assumed to be bad, harmful, undesirable – something to be avoided and excluded. By contrast, the scientific perspective is that whilst some chemicals are potentially very harmful, others are essential for life. Therefore, it is unhelpful when science communicators (whether journalists, or scientists themselves) use the term 'chemical' to refer only to potentially undesirable chemicals (which even then tend to be undesirable only in certain contexts), such as pesticides which are found in, and may harm, pollinators.
I decided to dig into the background of the item.
The news item
I found a news item in 'the Conversation' that discuses the work.
Dr Siviter's Article in the Conversation
It began
"A doctor will always ask if you are on any other medication before they write you a prescription. This is because pharmaceuticals can interact with each other and potentially disrupt the treatment, or even harm the patient. But when agrochemicals, such as pesticides, are licensed for use on farms, little attention is paid to how they interact with one another, and so their environmental impact is underestimated."
Siviter, 2021
This seemed a very good point, made with an analogy that seemed very telling.
"We analysed data gathered in scientific studies from the last two decades and found that when bees are exposed to a combination of pesticides, parasites and poor nutrition, the negative impact of each is exacerbated. We say that the cumulative effect of all these things is synergistic, meaning that the number of bees that are killed is more than we would predict if the negative effects were merely added together."
Siviter, 2021
This seems important work, and raises an issue we should be concerned about. The language used here was subtly different from in the radio programme:
"Many agrochemicals, such as neonicotinoids, are systemic, meaning they accumulate in the environment over several months, and in some cases years. It is perhaps not surprising then that honeybee colonies across the US have on average six different agrochemicals present in their wax, with one hive contaminated with 39 [sic, not 42]. It's not just honeybees which are at risk, though: wild bees such as bumblebees are also routinely exposed."
Siviter, 2021
So, here it was not 'chemicals' that were being counted but 'agrochemicals' (and the average figure of 6 now referred not to the colony as a whole, but only to the beeswax.)
The meta-analysis
'Agrochemicals' was also the term used in the research paper in the prestigious journal Naturewhere the research had been first reported,
"we conducted a meta-analysis of 356 interaction effect sizes from 90 studies in which bees were exposed to combinations of agrochemicals, nutritional stressors and/or parasites."
Siviter, et al., 2021
A meta-analysis is a type of secondary research study which collects results form a range of related published studies and seeks to identify overall patterns.
The original research
Moreover, the primary study being referred to as the source of the dubious statistic (i.e., that "the average number of chemicals found in a honey bee colony is six") referred not to 'chemicals' but to "pesticides and metabolites" (that is, substances which would be produced as the bee's metabolism broke the pesticides down):
"We have found 121 different pesticides and metabolites within 887 wax, pollen, bee and associated hive samples….
Almost all comb and foundation wax samples (98%) were contaminated with up to 204 and 94 ppm [parts per million], respectively, of fluvalinate and coumaphos, and lower amounts of amitraz degradates and chlorothalonil, with an average of 6 pesticide detections per sample and a high of 39."
Mullin, et al., 2010
Translation and representation
Scientific research is reported in research journals primarily for the benefit of other researchers in the field, and so is formatted and framed accordingly – and this is reflected in the language used in primary sources.
A model of the flow of scientific to public knowledge (after McInerney et al., 2004)
It is important that science which impacts on us all, and is often funded from public funds, is accessible to the public. Science journalism, is an important conduit for the communication of science, and for his to be effective it has to be composed with non-experts in the public in mind.
It is perfectly sensible and desirable for a scientist engaging with a public audience to moderate technical language to make the account of research more accessible for a non-specialist audience. This kind of simplification is also a core process in developing science curriculum and teaching.
However, in the case of 'chemical' I would suggest scientists take care with using the term (and avoid it if possible), as science teachers commonly have to persuade students that chemicals are all around of us, are not always bad for us, are part of us, and are essential. That pesticides and their breakdown products have been so widely detected in bee colonies is a matter of concern, as pesticides are substances that are used because of their detrimental effects on many insects and other organisms that might damage crops.
Whilst that is science deserving public attention, there are a good many more than 6 chemicals in any bee colony, and – indeed – we would want most of them to be there.
References:
McInerney, C., Bird, N., & Nucci, M. (2004). The Flow of Scientific Knowledge from Lab to the Lay Public: The Case of Genetically Modified Food. Science Communication, 26(1), 44-74. doi:10.1177/1075547004267024 https://journals.sagepub.com/doi/10.1177/1075547004267024
Mullin, C. A., Frazier, M., Frazier, J. L., Ashcraft, S., Simonds, R., vanEngelsdorp, D., & Pettis, J. S. (2010). High Levels of Miticides and Agrochemicals in North American Apiaries: Implications for Honey Bee Health. 5(3): e9754. PLoS ONE, 5(3), e9754. doi:10.1371/journal.pone.0009754 https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0009754
Siviter, H., Bailes, E. J., Martin, C. D., Oliver, T. R., Koricheva, J., Leadbeater, E., & Brown, M. J. F. (2021). Agrochemicals interact synergistically to increase bee mortality. Nature. doi:10.1038/s41586-021-03787-7 https://www.nature.com/articles/s41586-021-03787-7
Imagine the banks were contracted to deliver school teaching…employing their digital assistants
Keith S. Taber
The teacher of the future – imagine the government invited bids to 'deliver' schooling most cost-effectively (only a matter of time?), and the banks undercut schools by proposing to use their existing intelligent technology. Image by Gerd Altmann from Pixabay
Hi, I'm Rubis, your intelligent science teaching system. I can help with all sorts of everyday science learning queries. Let me know how I can help you today, or try asking me a short, simple question, such as "what is the formula of water?" and I'll be able to help.
Rubis, why is mercury a liquid at room temperature?
I didn't quite catch that, but I'm learning all the time.
Here are some of the top things that I get asked.
What are the three states of matter? Why are mushrooms not considered plants? What comes between gamma rays and ultraviolet radiation in the electromagnetic spectrum? Who invented gravity? Who was Archimedes' principal?
Rubis, why is mercury a liquid at room temperature?
One moment please, I'm just typing. Please select an option:
The periodic table The respiratory system Electrical resistance Acids Food webs
I'm trying to find out why mercury is a liquid at room temperature?
Just to check, do you mean:
What is the difference between a moon and a comet? How dangerous is ascorbic acid? Why is love like oxygen? 1 How can an acrobat balance on a trapezoid of forces? When did retroviruses come back into vogue? None of these
None of these
I can help with all sorts of everyday science learning queries. Try asking me a short, simple question, such as "what are the three ways in which heating occurs" and I'll be able to help.
…
Science teaching, of course, is a process that requires a well-prepared, highly knowledgeable, teacher who is sensitive to, and responsive to, individual learners whose moods and motivations shift from day to day and who may at any time ask a question that the teacher would never have predicted in advance. That's part of the joy (and challenge) of teaching, which when done well is an interactive process where the teacher has to make myriad real-time, 'on-line', decisions in response to a complex and ever changing context. That is, it requires a good deal of 'intelligence'.
Machine intelligence?
One (questionable) sign of 'progress' in our increasingly digital society is how getting access to costumer service usually involves perusing 'contact us' webpages that are designed to send you initially to fixed pages with answers to to 'FAQs' (frequently asked questions); only then offering 'chat' with an 'intelligent' assistant – which seems programmed to only pass you on to a human once it has recognised you have been sent round the same flow-chart loop more than once.
As I have pointed out before, this would be fine if these 'chat-bots' were actually intelligent (even in the limited sense of a learning machine).
My faux 'dialogue' above may seem an unfair parody. (Not a genuine dialogue of course as there was no meeting of minds and taking on board of the other's perspective.)
But if my bank (RBS) were to be given a contract to provide digital teaching services, I imagine it would be just like that. If they could do better, then surely their chat-bot for bank customers would be more useful and less frustrating.
The bank initiated the conversation…
My bank sent me an email suggesting that I would soon no longer be able to make on-line purchases with my debit card unless I used a mobile 'phone (which currently I do not, and am not planning to anytime soon). "As part of new regulations, we'll often ask you to confirm that it's really you who's making the purchase when you use your card to pay for something online. To do this, you'll need to enter a six-digit one-time passcode (OTP) that we'll send to your mobile phone." Of course the message also told me "Please do not reply to this email as the address is not monitored". Hm, so how do I get in touch…
Cora offers "support" and "an instant answer"
Cora, the chat-bot, could make no sense of my inquiry.
Of course no chat-bot (or teacher) could be expected to always respond to any random enquiry. When I was teaching I would not have been able to instantly answer a question from outside my teaching subjects…
"Sir, in what year did Hannibal Lecter cross the Alps with Elephants?" 2
Here, however, I was not raising some obscure topic that the Bank could not have anticipated, as I was RESPONDING to a conversation initiated by the Bank!
Connected with Cora
Perhaps I am being unreasonable?
Hey there. I'm Cora, your digital assistant. Let me know how I can help you today, or select one of the top questions that I am being asked:
Please select an option:
Close an account Change my details Order paying in book Cancel transaction
Cora – 12:00
I choose to let 'her' know how she can help me today:
I have just had an email from the bank, suggesting in future I will need a mobile phone to make online purchases. At the present time I have no need for nor intention of getting a mobile phone.
Keith
I didn't quite catch that, but I'm learning all the time.
Here are some of the top things that I get asked.
Please select an option:
Coronavirus support Unknown transaction Cancel transaction Pending transaction Change account details Make a payment
More
Cora – 12:01
More
selected
One moment please, I'm just typing.
Please select an option:
Check a statement Help logging in Paying in a cheque Struggling financially Check account info Refunds/Retail disputes None of the above
Cora – 12:02
None of the above
selected
I can help with all sorts of everyday banking queries. Try asking me a short, simple question, such as "how do I order a new card?" and I'll be able to help.
Cora – 12:02
I have just had an email from the bank, suggesting in future I will need a mobile phone to make online purchases. At the present time I have no need for nor intention of getting a mobile phone. Please explain how I should proceed.
Keith
Please select an option:
Just to check, do you mean:
Benefit Insurance Claim Manage receipts in app Check my eligibility Suspicious email Remove an account holder None of these
Cora – 12.03
Just to check?
None of these
selected
I didn't quite catch that, but I'm learning all the time.
Here are some of the top things that I get asked.
Please select an option:
Coronavirus support Unknown transaction Cancel transaction Pending transaction Change account details Make a payment
more
Cora – 12.03
more
selected
Please select an option:
Check a statement Help logging in Paying in a cheque Struggling financially Check account info Refunds/Retail disputes None of the above
Cora -12.03
None of the above
Selected
I can help with all sorts of everyday banking queries. Try asking me a short, simple question, such as "how do I order a new card?" and I'll be able to help.
Cora – 12:03
So, basically, Cora can help me as long as I ask a question she has specifically prepared for. I may as well have asked her how come a metal like mercury could be a liquid at room temperature.
Just imagine teachers behaved like that!
Original image by 14995841 from Pixabay
Footnotes:
1 apparently because if you get too much you will get too 'high', but if you do not get enough you will die
"Love is like oxygen You get too much, you get too high Not enough and you're gonna die Love gets you high"
2 This suggests a science joke:
What was the outcome when Hannibal crossed the alps with elephants?
I am not sure, but the offspring would have been infertile.
A faecal transplant is like wild flower seeds in some soil
Keith S. Taber
"Many animals naturally ate each other's poo…as a way of staying healthy" Prof. Tim Spector. (Original image by Debbie De Jager from Pixabay, with apologies to Monty Python)
I was listening to a podcast from 'Science Stories' (BBC Radio 4) about 'Lady Mary Montagu's Smallpox Experiment', where Naomi Alderman described how the aforementioned Lady Mary Wortley Montagu brought the practice of opening veins to introduce some smallpox into the body, as a way of protecting against the deadly disease, back from Turkey to Britain.
This was compared with the process of faecal transplantation which was apparently first used in China, and is increasingly being seen as a valuable treatment for some gut disorders. This is the process of ingesting, under carefully controlled conditions, some human faeces – either some of your own carefully preserved (for example, some cancer patients have a sample collected and stored before starting chemotherapy), or from some donor who is willing to offer some of their own. Unlike some other donor procedures (such as kidney donation) this is non-invasive and concerns material most of us just dispose of anyway!
Tim Spector, Professor of Genetic Epidemiology at Kings College, London explained the significance of the gut microbiome, the community of something like 100 trillion microbes that typically occupy a human gut. The importance of these organisms for human health is increasingly being appreciated.
Treating Clostridium difficile infection
Disturbances of the gut microbiome can lead to ill health. One particular example is the condition known as Clostridium difficile infection ('C. diff') – which is commonly experienced in hospitals when patients have extensive courses of antiobiotics – which can sadly kill the useful gut microbes as well those disease-causing organisms being targeted. Clostridium difficile (being itself unaffected by many commonly used antibiotics) can in these circumstances reproduce rapidly and vastly increase its numbers. This is problematic as the organism releases a toxin.
C. diff infection can lead to the sufferer needing to visit the toilet urgently and repeatedly – many times each day. This is not only undesirable in itself, but interferes with getting nutrition from food (if the person has any appetite to eat), and leads to dangerous dehydration – and can have other complications. So, this is a very serious condition, and it is readily transmitted from one person to another.
"C. difficile is an infectious Gram-positive spore-forming bacillus microorganism of the gastrointestinal tract, and its toxin expression causes gastrointestinal illness with a wide spectrum of severity, ranging from mild diarrhea to pseudomembranous colitis, toxic megacolon, sepsis-like picture and death…"
Bien, Palagan & Bozko, 2013: 53
Many people have a low level of Clostridium difficile specimens in their gut normally, but as one small part of the much larger and diverse population of gut microbes – in which context they cause no problems.
"C. difficile does not cause any significant disease when it is present in small numbers. However, disturbance of the normal intestinal flora (dysbiosis) by several potential causative factors may result in unlimited [sic] expansion of C. difficile in the microbiota, leading to inflammation and damage of the gut mucosa…"
Bien, Palagan & Bozko, 2013: 56
Someone who has suffered from C. diff infection needs a way to repopulate their gut with a good range of the usual different microbes. And that is when consuming a sample of a healthy person's excrement can be useful. (This is of course done under medical direction and supervision, both to maintain hygiene and to ensure the donor does not have medical conditions that might be passed on with the sample.)
A teaching analogy for faecal transplantation
This was all explained by Prof. Spector using an analogy.
Analogies are comparisons where a less familiar, and perhaps abstract or counterintuitive, concept is explained in terms of something familiar that can be seen to have a similar conceptual structure (see the figure). Analogies are commonly used in science teaching and public communication of science (as here in a radio programme) to introduce scientific ideas.
Figure: A teaching analogy to explain why faecal transplantation can be used to treat C. diff (based on the presentation by Prof. Tim Spector in 'Lady Mary Montagu's Smallpox Experiment')
How does your garden grow?
Prof. Spector developed a comparison between the different microbes found in the gut, and the plants growing in a garden:
"These nasty infections are the most extreme, if you like, that pretty much wipe out most of our normal species. So … we might, say, start with a thousand species and people [with C. diff] might be down to just ten or so, different ones and so nasty ones take over. It's a bit like a garden that has gone very badly wrong and you have put too much herbicide all over it and it looks like an Arizona back yard with a few burning tyres in it. It's very easy for things to take over that and what we want to get, is by putting these bugs in there, to create a really healthy garden that gets back to normal that looks like a nice English country garden with lots of blooms, and really good soil, and lots of plants interacting with each other, and that's the way to think about these microbes, but to do that, to get to this nice rosy picture of a country garden you have to go through yucky stages first"
Before and after faecal transplantation: a medical treatment that can transform your 'garden'? (Images by Simon (left) and Prawny (right) from Pixabay) [Move the slider to change between the pictures].
So the idea of taking a sample of someone else's excrement into our own gut may seem "yukky" – and is definitely NOT recommended without proper procedures and supervision – but may sometimes be a sensible and beneficial medical treatment. Just think of it as resewing the garden of the gut with a nice selection of seeds that will give rise to a diverse selection of colourful blooms.
Naomi Alderman: Instead of poo, we could think to ourselves, 'wild flower seeds'
Tim Spector: It's wild flower seeds with a bit of soil in it as well, so they have come in their own pot [sic] if you like.
'wild flower seeds with a bit of soil…in their own pot'? (Images by OpenClipart-Vectors from Pixabay)
Work cited:
Bien, J., Palagani, V., & Bozko, P. (2013). The intestinal microbiota dysbiosis and Clostridium difficile infection: is there a relationship with inflammatory bowel disease? Therapeutic advances in gastroenterology, 6(1), 53-68. doi:10.1177/1756283X12454590 https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3539291/
As part of the primary scientific literature, it publishes articles written by specialist scientists in a technical language intended to be understood by other specialists. Dense scientific terminology is not used to deliberately exclude general readers (as sometimes suggested), but is necessary for scientists to make a convincing case for new knowledge claims that seem persuasive to other specialists. This requires being precise, using unambiguous technical language."The thingamajig kind of, er, attaches to the erm, floppy bit, sort of" would not do the job.
Science News however is news media – it publishes journalism (indeed, 'since 1921' the site reports – although that's the publication and not its website of course.) While science journalism is not essential to the internal processes of science (which rely on researchers engaging with each other's work though scholarly critique and dialogue) it is very important for the public's engagement with science, and for the accountability of researchers to the wider community.
Science journalists have a job similar to science teachers – to communicate abstract ideas in a way that makes sense to their audience. So, they need to interpret research and explain it in ways that non-specialists can understand.
The news article told me
"Like a shaggy dog in springtime, some black holes have to shed… Unlike dogs with their varied fur coats, isolated black holes are mostly identical. They are characterized by only their mass, spin and electric charge. According to a rule known as the no-hair theorem, any other distinguishing characteristics, or "hair," are quickly cast off. That includes magnetic fields."
Conover, 2013
Here there is clearly the use of an analogy – as a black hole is not the kind of thing that has actual hair. This would seem to be an example of a journalist creating an analogy (just as a science teacher would) to help 'make the unfamiliar familiar' to her readers:
just as
dogs with lots of hair need to shed some ready for the warmer weather (a reference to a familiar everyday situation)
so, too, do
black holes (no so familiar to most people) need to lose their hair…
Surely a better analogy would be along the lines that just as dogs with lots of hair need to shed some ready for the warmer weather, so to do black holes need to lose their magnetic fields…
An analogy is used to show a novel conceptual structure (here, relating to magnetic fields around black holes) maps onto a more familiar, or more readily appreciated, one (here, that a shaggy dog will shed some of its fur). A teaching analogy may not reflect a deep parallel between two systems, as its function may be just to introduce an abstract principle.
Conover did not invent the 'hair' reference for her ScienceNews piece – rather she built her analogy on a term used by the scientists themselves. Indeed, the title of the cited research journal article was "Magnetic Hair and Reconnection in Black Hole Magnetospheres", and it was a study exploring the consequences of the "no-hair theorem" – as the authors explained in their abstract:
"The no-hair theorem of general relativity states that isolated black holes are characterized [completely described] by three parameters: mass, spin, and charge."
Bransgrove, Ripperda & Philippov, 2021
However, some black holes "are born with magnetic fields" or may "acquire magnetic flux later in life", in which case the fields will vary between black holes (giving an additional parameter for distinguishing them). The theory suggests that these black holes should somehow lose any such field: that is, "The fate of the magnetic flux (hair) on the event horizon should be in accordance with the no-hair theorem of general relativity" (Bransgrove, Ripperda & Philippov, 2021: 1). There would have to be a mechanism by which this occurs (as energy will be conserved, even when dealing with black holes).
So, the study was designed to explore whether such black holes would indeed lose their 'hair'. Despite the use of this accessible comparison (magnetic flux as 'hair'), the text of the paper is pretty heavy going for someone not familiar with that area of science:
"stationary, asymptotically flat BH spacetimes…multipole component l of a magnetic field…self-regulated plasma…electron-positron discharges…nonzero stress-energy tensor…instability…plasmoids…reconnection layer…relativistic velocities…highly magnetized collisionless plasma…Lundquist number regime…Kerr-schild coordinates…dimensionless BH spin…ergosphere volume…spatial hypersurfaces…[…and so it continues]"
(Bransgrove, Ripperda & Philippov, 2021: 1).
"Come on Harry, you know full well that 'the characteristic minimum plasma density required to support the rotating magnetosphere is the Goldreich-Julian number density' [Bransgrove, Ripperda & Philippov, 2021: 2], so hand me that hyperspanner." Image from Star Trek: Voyager (Paramount Pictures)
Spoiler alert
I do not think I will spoil anything by revealing that Bransgrove and colleague conclude from their work that "the no-hair theorem holds": that there is a 'balding process' – the magnetic field decays ("all components of the stress-energy tensor decay exponentially in time"). If any one reading this is wondering how they did this work, given that most laboratory stores do not keep black holes in stock to issue to researchers on request, it is worth noting the study was based on a computer simulation.
That may seem to be rather underwhelming as the researchers are just reporting what happens in a computer model, but a lot of cutting-edge science is done that way. Moreover, their simulations produced predictions of how the collapsing magnetic fields of real black holes might actually be detected in terms of the kinds of radiation that should be produced.
As the news item explained matters:
Magnetic reconnection in balding black holes could spew X-rays that astronomers could detect. So scientists may one day glimpse a black hole losing its hair.
Conover, 2013
So, we have hairy black holes that go through a balding process when they lose their hair – which can be tested in principle because they will be spewing radiation.
Balding is to hair, as…
Here we have an example of an analogy for a scientific concept. Analogies compare one phenomenon or concept to another which is considered to have some structural similarity (as in the figure above). When used in teaching and science communication such analogies offer one way to make the unfamiliar familiar, by showing how the unfamiliar system maps in some sense onto a more familiar one.
hair = magnetic field
balding = shedding the magnetic field
Black holes are expected to be, or at least to become, 'hairless' – so without having magnetic fields detectable from outside the event horizon (the 'surface' connecting points beyond which everything, even light, is unable to 'escape' the gravitational field and leave the black hole). If black holes are formed with, or acquire, such magnetic fields, then there is expected to be a 'balding' process. This study explored how this might work in certain types of (simulated) black holes – as magnetic field lines (that initially cross the event horizon) break apart and reconnect. (Note that in this description the magnetic field lines – imaginary lines invented by Michael Faraday as a mental tool to think about and visualise magnetic fields – are treated as though they are real objects!)
Some such comparisons are deliberately intended to help scientists explain their ideas to the public – but scientists also use such tactics to communicate to each other (sometimes in frivolous or humorous ways) and in these cases such expressions may do useful work as short-hand expressions.
So, in this context hair denotes anything that can be detected and measured from outside a black hole apart form its mass, spin, and charge (see, it is much easier to say 'hair')- such as magnetic flux density if there is a magnetic field emerging from the black hole.
A dead metaphor?
In the research paper, Bransgrove, Ripperda and Philippov do not use the 'hair' comparison as an analogy to explain ideas about black holes. Rather they take the already well-established no-hair theorem as given background to their study ("The original no-hair conjecture states that…"), and simply explain their work in relation to it ("The fate of the magnetic flux (hair) on the event horizon should be in accordance with the no-hair theorem of general relativity.")
Whereas an analogy uses an explicit comparison (this is like that because…), a comparison that is not explained is best seen as a metaphor. A metaphor has 'hidden meaning'. Unlike in an analogy, the meaning is only implied.
"The no-hair theorem of general relativity states that isolated black holes are characterized by three parameters: mass, spin, and charge";
"The original no-hair conjecture states that all stationary, asymptotically flat BH [black hole] spacetimes should be completely described by the mass, angular momentum, and electric charge"
Bransgrove and colleagues do not need to explain why they use the term 'hair' in their research report as in their community it has become an accepted expression where researchers already know what it is intended to mean. We might consider it a dead metaphor, an expression which was originally used to imply meaning through some kind of comparison, but which through habitual use has taken on literal meaning.
Science has lots of these dead metaphors – terms like electrical charge and electron spin have with repeated use over time earned their meanings without now needing recourse to their origins as metaphors. This can cause confusion as, for example, a learner may develop alternative conceptions about electron spin if they do not appreciate its origin as a metaphor, and assumes an electron spins in the same sense as as spinning top or the earth in space. Then there is an associative learning impediment as the learner assumes an electron is spinning on its axis because of the learner's (perfectly reasonable) associations for the word 'spin'.
The journalist or 'science writer' (such as Emily Conover), however, is writing for a non-specialist readership, so does need to explain the 'hair' reference. So, I would characterise the same use of the terms hair/no-hair and balding as comprising a science analogy in the news item, but a dead metaphor in the context of the research paper. The meaning of language, after all, is in the mind of the reader.
The unbelievable truth – do bacteria focus incident light onto their back-sides, so they can tell which way to go?
"Bacteria are just tiny eyeballs" sounds like another science analogy, but is actually something I learned today from BBC Radio 4.
On David Mitchell's "The Unbelievable Truth" panelists read essays on a topic, but populated with false (and preferably funny) statements. The premise is great: the panelists try to sneak in some true facts which sound so unlikely that they are confused with the falsehoods. Panelists get marks for correctly spotting truths in another panelist's little essay, or for completing their own talk with some of their 'unbelievable' truths not being spotted.
On today's episode I was shocked top learn from Dr Ria Lina that "…bacteria are just tiny eyeballs…".
Because they are not.
Well, not exactly…
Her essay was talking about germs, and included:
"Transmission of disease is determined by how many victims germs can actually see. Viruses have load of tiny little eyes so they are able to see loads and loads of potential victims in all different directions, whereas bacteria are just tiny little eyeballs, and fungi are extremely short sighted poor things, which is why they are only able to infect places like feet."
At the end of the round, David reported that the part about bacteria as eyes was true, although he did not seem very convinced:
David: You have managed to smuggle three truth past the rest of the panel, which are that bacteria are just tiny eyeballs – although to me that sounds a bit like things being put into language that people understand, because they are not like tiny eyeballs, really are they?
Ria: Well the light goes in and it reflects off the back surface which acts like a rudimentary retina…
Right,
…and also you have got to remember that the eye had evolved multiple times in multiple ways, so the squid eye and the human eye even though they both work the same way did not come from the same universal ancestor…
Oh right
…so, bacterial eye is basically what we are seeing now is the beginning of – [sadly interrupted by another panelist]. I'm such a geek…
Ria Lina – self-confessed geek (and there is nothing wrong with that)
I presumed there must be some basis for this claim; that Dr Lina (PhD in viral bioinformatics) must be drawing upon some actual science, but I was not sure what. Whereas the eyeball has a back surface there is no inherent back surface for a bacterium – so this must mean any inside surface.
Although light does reflect off the retina (red eye in camera images is due to the light reflecting from the retina with its rich supply of blood vessels) – the function of the retina is to absorb light and to then signal information forward based on the pattern of light detected. Some species have a reflecting layer (tapetum lucidum) behind the retina to increase efficiency – some light not absorbed by the retina initially gets a second pass though after reflection which allows increased absorption. But this is only useful because there are cells capable of absorbing the light and processing information based on the absorption.
The bacterium is a single cell, so the most sense I could make of this is that when light absorption is useful, a reflecting inner surface could be valuable. This might make sense for cyanobacteria to increase the efficiency of photosynthesis by reflecting light not absorbed on the first pass.
What did we do before the internet?
I did some quick searching on line.
Someone had developed a method of identifying bacterial colonies through light back-scattered, which was useful because the technique using transmitted light was impractical in species that absorb most of the incident light.
Interesting, but the light was not being reflected internally, if I understood the paper.
Someone has developed a technique to increase the light absorbed by photosynthetic algae and cyanobacteria that did use total internal reflection – but if I read correctly this reflection is in the light guide on the way to the cell, not inside it.
Image by Stephan Ernst from Pixabay
So, I was still not buying the eyeballs story. Then I found a report of how "Cyanobacteria use micro-optics to sense light direction",
"Here, we establish that individual Synechocystis cells can directly and accurately perceive the position of a unidirectional light source, and control their motility so as to move towards it. We then show that Synechocystis cells act as microlenses, and that the light intensity gradient across the cell due to this lensing effect is far greater than the effects of shading due to light absorption or reflection. Finally, we use highly-localized laser excitation to show that specific excitation of one side of the cell triggers movement away from the light, indicating that positive phototaxis results from movement away from an image of the light source focused on the opposite side of the cell. Essentially, the cell acts as a microscopic eyeball."
Schuergers et al.,2016
Wow, nature never ceases to amaze.
So, basically the cell itself focuses incident light to be concentrated at the 'back' of the cell (where back is the side opposite the light source), organelles that absorb light can in effect detect this light 'spot', and the bacterium has evolved to move 'forward' towards the light source based on where in the cell this higher light intensity occurs. The system in effect 'knows' which direction to take as forward.
"Here we have shown that Synechocystis cells act as very effective spherical microlenses that focus a sharp image of a light source at the opposite edge of the cell. This implies that positive phototaxis (i.e. movement towards a light source) is actually triggered as a negative response to the focused spot of light at rear periphery of the cell."
Schuergers et al.,2016
This does not seem to involve internal reflection, so perhaps there is another source for the eyeballs claim (possibly with an even more amazing nugget of science) that I have missed and which was the basis of Dr Lina's claim.
Bacteria are not just tiny eyeballs, but…
I still think it is not correct to claim that "bacteria [generally, or even this particular bacteria] are just tiny eyeballs". This is a simplification, and probably not an 'intellectually honest' one that could be considered to be at the 'optimum level of simplification' for communicating a key scientific idea stripped of distracting complications.
Indeed the real wonder of Synechocystis is that it a single cell that acts as an integrated, responsive, coherent system: energy collection unit, eyeball, lens, photo-receptors, controller/processor, and locomotive unit.
Despite this quibble, given the context of the claim (made as part of a comedy show, not a peer reviewed research conference) I think I am impressed enough to have to revise the 'Tweet' I was going to send Dr Lina calling her out for telling an unbelievable lie on national radio. I should have remembered that it is very difficult to come up with any claim about the living world which is so fantastic that one can be confident there is not an example of a species out there which affirms the claim. When it comes to nature we often need to believe the unbelievable truth.
Work cited:
Huisung Kim, Iyll-Joon Doh, Jennifer Sturgis, Arun K. Bhunia, J. Paul Robinson, Euiwon Bae (2016) Reflected scatterometry for noninvasive interrogation of bacterial colonies, Journal of Biomedical Optics. 21(10), 107004, doi: 10.1117/1.JBO.21.10.107004.
Ooms, M. D., Sieben, V. J., Pierobon, S. C., Jung, E. E., Kalontarov, M., Erickson, D., & Sinton, D. (2012). Evanescent photosynthesis: exciting cyanobacteria in a surface-confined light field. Physical Chemistry Chemical Physics, 14(14), 4817-4823. doi:10.1039/C2CP40271H
Schuergers, N., Lenn, T., Kampmann, R., Meissner, M. V., Esteves, T., Temerinac-Ott, M., . . . Wilde, A. (2016). Cyanobacteria use micro-optics to sense light direction. Elife, 5, e12620.
Is the work of cognition like the work of a palaeontologist? (Image by Brenda Geisse from Pixabay)
I like the reflexive nature of this account – of someone reconstructing an analogy
abouthow cognition reconstructs coherent wholes from partial, fragmented data
froma partial, fragmented memory representation.
I was reading something about memory function that piqued my interest in an analogy:
"Neisser, using an analogy initially developed by Hebb (1949) to characterize [sic] perception, likened the rememberer to a paleontologist who attempts to reconstruct a dinosaur from fragmentary remains: 'out of a few stored bone chips, we remember a dinosaur'…"
Schacter, 1995, p.10
I was interested enough to look up the original use of this analogy (as I report below).
This links to three things that have separately interested me:
the nature of memory
the constructivist account of learning and cognition
using analogies in teaching and comunicating science
The nature of our memories
I have long been interested in what memory is and how it works – and its role in academic learning (Taber, 2003). In part this perhaps derives from the limits of my own memory – I have been reasonably successful academically, but have never felt I had a good memory (and I seem to get more 'absent minded' all the time). This interest grew as it became clearer to me that our memory experiences seem to be quite different – my late wife Philippa would automatically and effortlessly remember things in a way that that seemed to me to be a kind of superpower. (She was once genuinely surprised that I could not picture what a family member had been wearing on arriving at a family event years before, whereas I thought I was doing pretty well to even remember I had been there.) Now that neurodiversity is widely recognised, it seems less surprising that we do not all experience memory in the same way.
A lot of people, however, understand memory in terms of a kind of folk-model (that is, a popular everyday account which does not match current scientific understanding) – along the lines that we put information into a memory store, where – unless it gets lost and we forget – we can later access it and so remember what it was that we committed to memory. Despite the ubiquity of that notion, research suggests that is not really how memory functions. We might say that this is a common alternative conception of how memory works.
Schacter was referring back to a tradition that began a century ago when Bartlett carried out a series of studies on memory. Bartlett (1932/1995) would, for example, expose people to a story that was unfamiliar to his study participants, and then later ask them to retell as much of the story as they could remember. As might be expected, some people remembered more details than others.
What perhaps was less predictable at the time was the extent to which people included in their retelling details that had not been part of the original story at all. These people were not deliberately embellishing or knowingly guessing, but reporting, as best they could, what their memory suggested had been part of the original story.
People who habitually exhibit this 'confabulation' to an pathological degree (perhaps remembering totally fantastic things that clearly could not be true) are recognised as having some kind of problem, but it transpires this is just an extreme of something that is normal behavior. Remembering is not the 'pulling something out of storage' that we may experience it as – as actually what we remember is more like a best guess based on insufficient data (but a guess made preconsciously, so it appears in our conscious minds as definitive) than a pristine copy of an original experience. Memory is often more a matter of constructing an account from the materials at hand than simply reading it out from something stored.
Thus the analogy. Here is some wider context for the quote presented above:
"The publication of Neisser's (1967) important monograph on cognitive psychology rekindled interest in Bartlett's ideas about schemas and reconstructive memory. According to Neisser, remembering the past is not a simple matter of reawakening a dormant engram or memory trace; past events are constructed by using preexisting knowledge and [schemata] to piece together whatever fragmentary remains of the initial episode are available in memory. Neisser, using an analogy initially developed by Hebb (1949) to characterize [sic] perception, likened the rememberer to a paleontologist who attempts to reconstruct a dinosaur from fragmentary remains: 'out of a few stored bone chips, we remember a dinosaur' (1967, p.285). In this view, all memories are constructions because they include general knowledge that was not part of a specific event, but is necessary to reconstruct it. The fundamentally constructive nature of memory in turn makes it susceptible to various kinds of distortions and inaccuracies. Not surprisingly, Neisser embraced Bartlett's observations and ideas about the nature of memory."
Schacter, 1995, p.10
These ideas will not seem strange to those who have studied science education, a field which has been strongly influenced by a 'constructivist' perspective on learning. Drawing on learning science research, the constructivist perspective focuses on how each learner has to build up their own knowledge incrementally: it is not possible for a teacher to take some complex technical knowledge and simply transfer it (or copy it) to a learner's mind wholesale.
Excavating the analogy: what did Hebb actually say?
Hebb is remembered for his work on understanding the brain in terms of neural structures – neurons connected into assemblies through synapses. His book 'The Organization of Behavior' has been described as "one of the most influential books in Psychology and Neuroscience" (Brown, 2020: 1).
The analogy referred to by Schacter was used by Hebb in describing perception. He discussed studies using a tachistoscope, an instrument for displaying images for very brief periods. This could be used to show an image to a person with an exposure insufficient for them to take in all the details,
"…the pattern is perceived, first, as a familiar one, and then with something missing or something added. The something, also, is familiar; so the total perception is a mélange of the habitual.
The subject's reports [make it] clear that the subject is not only responding to the diagram as a whole; he perceives its parts as separate entities, even though presentation is so brief. Errors are prominent, and such as to show that all the subject really perceives–and then only with rough accuracy–is the slope of a few lines and their direction and distance from one another"
Hebb, 1949: pp.46-47
That is, the cognitive system uses the 'clues' available from the incomplete visual data to build (in effect) a hypothesis of what was seen, based on correspondences between the data actually available and familiar images that match that limited data. What the person becomes consciously aware of 'seeing' is not actually a direct report from the visual field of the presented image, but a constructed image that is a kind of conjecture of what might have been seen – 'filling-in' missing data with what seems most likely based on past visual experiences.
Cognitive scientist Annette Karmiloff-Smith developed the concept of 'representational redescription' as a way of describing how initially tacit knowledge could eventually become explicit. She suggested that "intra-domain and inter-domain representational relations are the hallmark of a flexible and creative cognitive system" (Karmiloff-Smith,1996: 192). The gist was that the brain is able to re-represent its own internal representations in new forms with different affordances.
An loose analogy might be someone who takes a screenshot when displaying an image from the JPEG photo collection folder on the computer, opens the screenshot as a pdf file, and then adds some textual annotations before exporting the file to a new pdf. The representation of the original image is unchanged in the system, but a new representation has been made of it in a different form, which has then been modified and 'stored' (represented) in a different folder.
Hebb was describing how a representation of visual data at one level in the cognitive system has been represented elsewhere in the system (representational redescription?) at a level where it can be mentipulated by 'filling-in'.
Hebb then goes on to use the analogy:
"A drawing or a report of what is seen tachistoscopically is not unlike a paleontologist's reconstruction of early man from a tooth and a rib. There is a clear effect of earlier experience, filling in gaps in the actual perception, so that the end result is either something familiar or a combination of familiar things–a reconstruction on the basis of experience."
Hebb, 1949: p.47
Teaching analogies
Hebb was writing a book that can be considered as a textbook, so this can be seen as a teaching analogy, although such analogies are also used in communicating science in other contexts.
Teaching is about making the unfamiliar familiar, and one way we do that is by saying that 'this unfamiliar thing you need to learn about is a bit like this other thing that you already know about'. Of course, when teaching in this way we need to say in what way there is an analogy, and it may also be important to say in what ways the two things are not alike if we do not want people to map across irrelevant elements (i.e., to develop 'associative' learning impediments).
Hebb is saying that visual perception is often not simply the detection of a coherent and integral image, but is rather a construction produced by building upon the available data to construct a coherent and integral image. In extremis, a good deal may be made of very little scraps of input – akin to a scientist reconstructing a model of a full humanoid body based on a couple of bits of bone or tooth.
Hebb's analogy
There are examples where palaeontologists or anthropologists have indeed suggested such complete forms based on a few fossil fragments as data. This is only possible because of their past experiences of meeting many complete forms, and the parts of which they are made. (And of course, sometimes other scientists completely disagree about their reconstructions!)
An exscientific analogy?
Often in teaching science we use teaching analogies that compare an unfamiliar scientific concept to some familiar everyday phenomenon – perhaps a reaction profile is a bit like a roller-coaster track. Perhaps we could call these adscientific analogies as the meaning is transferred to the scientific concept from the everyday.
Sometimes, however, familiar scientific phenomena or ideas are used as the source – as here. Perhaps these could be called exscientific analogies as the meaning is taken from the science concept and applied elsewhere.
Developing the palaeontology analogy
So, Hebb had originally used the palaeontology analogy in the context of discussing perception. When I looked into how Neisser had used the comparison in his "important monograph on cognitive psychology" I found he had developed the analogy, returning to it at several points in his book.
Do we analyse what we attend to?
Neisser's first reference was also in relation to perception, rather than memory. Neisser argued that before we can attend to part of a scene there must already have been the operation of "preattentive mechanisms, which form segregated objects" from which we can select what to attend to. These processes might be referred to as analyses:
"…the detailed properties and features that we ordinarily see in an attended figure…arise…only because part of the input was selected for attention and certain operations then performed on it. Neither the object of analysis nor the nature of the analysis is inevitable, and both may vary in different observers and at different times."
Neisser, 1967, p.94
But Neisser was not sure this really was 'analysis', which he understood as drawing on another (what I labelled above) exscientific analogy:
"The very word 'analysis' may not be apt. It suggests an analogy with chemistry: a chemist 'analyses' unknown substances to find out what they 'really' are."
Neisser, 1967, p.94
Rather than refer to analysis, we could draw on Hebb's palaeontological analogy:
"More appropriate…is Hebb's (1949, p.47) comparison of the perceiver with a paleontologist, who carefully extracts a few fragments of what might be bones from a mass of irrelevant rubble and 'reconstructs' the dinosaur that will eventually stand in the Museum of Natural History. In this sense it is important to think of focal attention as a constructive, synthetic activity rather than as purely analytic. One does not simply examine the input and make a decision; one builds an appropriate visual object."
Neisser draws upon the analogy repeatedly in developing his account of perception:
"Such emotion-flooded experiences [as 'physiognomic' perception: 'Everyone has perceived such traits as suppressed anger in a face, gaiety in a movement, or peaceful harmony in a picture'] can be thought of as the result of particular kinds of construction. The same fragments of bone that lead one paleontologist to make an accurate model of an unspectacular creature might lead another, perhaps more anxious or more dramatic, to 'reconstruct' a nightmarish monster." (pp.96-97)
"To 'direct attention' to a figure is to attempt a more extensive synthesis of it. Of course, synthesis presupposes some prior analysis, as the paleontologist must have some fragments of bone before he can build his dinosaur…" (p.103)
"Recognition, whether of spelling patterns or words as wholes, must be mediated by relevant features, as meaningless in themselves as the bone chips of the paleontologist." (p.114)
"The process of figural synthesis does not depend only on the features extracted from the input, just as the dinosaur constructed by a paleontologist is not based only on the bone chips he has found. Equally important is the kind of perceptual object the perceiver is prepared to construct. The importance of set and context on the perception of words has been demonstrated in a great many experiments." (pp.115-116)
Neisser, 1967
And as with perception, so memory…
When Neisser discusses memory he uses a kind of double analogy – suggesting that memory is a bit like perception, which (as already established) is a bit like the work of the palaeontologist:
"Perception is constructive, but the input information often plays the largest single role in determining the constructive process. A very similar role, it seems to me, is played by the aggregate of information stored in long-term memory.
This is not to say that the stimuli themselves are copied and stored; far from it. The analogy being offered asserts only that the role which stored information plays in recall is like the role which stimulus information plays in perception….The model of the paleontologist, which was applied to perception and focal attention in Chapter 4, applies also to memory: out of a few stored bone chips, we remember a dinosaur….one does not recall objects or responses simply because traces of them exist in the mind, but after an elaborate process of reconstruction, (which usually makes use of relevant stored information).
What is the information – the bone chips – on which reconstruction is based? The only plausible possibility is that it consists of traces of prior processes of construction. There are no stored copies of finished mental events, like images or sentences, but only traces of earlier constructive activity."
Neisser, 1967, p.285
Fleshing-out the metaphor
Neisser then pushes the analogy one step further, by pointing out that the 'fleshed-out' model of a dinosaur in the museum may be constructed in part based on the fossil fragments of bones, but those fragments themselves do not form part of the construction (the model). The bones are used as referents in building the skeletal framework (literally, the skeleton) around which the model will be built, but the model is made from other materials (wood, steel, fibreglass, whatever) and the fossil fragments themselves will be displayed separately or perhaps filed away in a drawer in the museum archives. (As in the representational redescription model – the original representation is redescribed at another level of the system.)
"The present proposal is, therefore, that we store traces of earlier cognitive acts, not of the products of those acts. The traces are not simply 'revised' or 'reactivated' in recall; instead, the stored fragments are used as information to support a new construction. It is as if the bone fragments used by the paleontologist did not appear in the model he builds at all – as indeed they need not, if it to represent a fully fleshed-out skin-covered dinosaur. The bones can be thought of, somewhat loosely, as remnants of the structure which created and supported the original dinosaur, and thus as sources of information about how to reconstruct it."
Neisser, 1967, pp.285-286
Neisser's development of Hebb's analogy
The head palaeontologist?
A final reference to the analogy is used when Neisser addresses the question of the cognitive executive: the notion that somewhere in the cognitive system there is something akin to an overseer who direct operations:
"Who does the turning, the trying, and the erring" Is there a little man in the head, a homonculus, who acts the part of the paleontologist vis-à-vis the dinosaur? p.293
Neisser, 1967, p.293
The homonculus can be pictured as a small person sitting in the brain's control room, for example, viewing the images being projected from the visual input.
It is usually considered this is a flawed model (potentially lading to an infinite regress), a failure to take a systemic view of the cognitive system. It is the system which functions and leads to our conscious experience of perceiving, attending, making decisions, planning, remembering, and so forth. Whilst there are specialist components (modules) including for the coordination of the system, there is not a discrete controller overlaying the system as a whole who is doing the seeing, hearing, thinking, etcetera based on outputs from processing by the system.
Here the homonculus would like an authority that the palaeontologist turned to in order to decide how to build her model: raising the question of how does that expert know, and who would they, in turn, ask?
Why change Hebb's orignal analogy?
Altohugh Neisser refers to the analogy as being that used by Hebb, he modifies it. A tooth and rib become fragments of bone, and the early man becomes a dinosaur. Whether the shift from the reconstruction of an early hominid to the reconstruction of a terrible lizard was a deliberate one (for greater effect? because Neisser thought it would be more familiar to his readers?) or not I do not know. The phrasing suggests that Neisser thought he was applying Hebb's original comparison – so I suspect this is how he recalled the analogy.
Perhaps Neisser had regularly used the analogy in his teaching, in which case it may have become so familiar to him that he did not feel the need to check the original version. That is, perhaps he was correctly remembering how he had previously misremembered the original analogy. That is not fanciful, as memory researchers suggest this is something that is very common. Each time we access a memory the wider representational context becomes modified by engagement with it.
That is, if what is represented (in 'long-term memory'*) is indeed "traces of prior processes of construction…traces of earlier constructive activity" then each time a 'memory' is experienced, by being constructed based on what is represented ('in memory'*), new traces of that process of constructing the memory are left in the system.
It is possible over the years to be very convinced about the accuracy of a distorted memory that has been regularly reinforced. (The extent to which this may in part be the origin of many wars, feuds, and divorces might be a useful focus for research?)
So perhaps Neisser had represented in his long-term memory the analogy of a palaeontologist with a few fossil fragments, and when he sought to access the analogy, perhaps in a classroom presentation, the other elements were filled-in: the 'tooth and rib' became 'a few fragments of what might be bones' and the 'early man' become 'a dinosaur' – details that made sense of the analogy in terms familiar to Neisser.
The account of cognition that Hebb, Neisser and Schater were presenting would suggest that if this had been the case then for Neisser there would be no apparent distinction between the parts of Hebb's analogy that Neisser was remembering accurately, and the parts his preconscious mind had filled-in to construct a coherent analogy. I like the reflexive nature of this account – of someone reconstructing an analogy about how cognition reconstructs coherent wholes from partial, fragmented data – from a partial, fragmented memory representation.
Sources cited:
Bartlett, F. C. (1932/1995). Remembering: A study in experimental and social psychology Cambridge: Cambridge University Press.
Brown, R. E. (2020). Donald O. Hebb and the Organization of Behavior: 17 years in the writing. Molecular Brain, 13(1), 55. doi:10.1186/s13041-020-00567-8
Hebb, D. O. (1949). The Organisation of Behaviour. A neuropsychological theory. New York: John Wiley & Sons, Inc.
Karmiloff-Smith, A. (1996). Beyond Modularity: A developmental perspective on cognitive science. Cambridge, Massachusetts: MIT Press.
Neisser, U. (1967). Cognitive Psychology. New York: Appleton-Century-Crofts.
Schacter, D. L. (1995). Memory distortion: history and current status. In D. L. Schacter (Ed.), Memory Distortion. How minds, brains, and societies reconstruct the past (pp. 1-43). Cambridge, Massachusetts: Harvard University Press.
* terms like 'in memory' and 'in long-term memory' may bring to mind the folk-notion of memory as somewhere in the brain where things are stored away, whereas it is probably better to think of the brain as a somewhat plastic processing system which is constantly being modified by its own functioning. The memory we experience is simply the outcome of active processing** in part of the system that has previously been modified by earlier mental activity (** active processing which is in turn itself further modifying the system).
Unseen minerals all around us (Ockham's Razor – ABC)
I was listening to a recent episode of 'Ockhams' razor' (ABC's series of short science and technology essays) from 2020 called 'Unseen minerals all around us'. As a radio programme, the audience was likely to be diverse in terms of age, interests, and background knowledge and experiences.
The speaker was Allison Britt, Director of Mineral Resources Advice and Promotion, Geoscience Australia ("Australia's pre-eminent public sector geoscience organisation"), and she was describing the large number of elements used in constructing a modern mobile phone – apparently someone had put a phone in a laboratory blender and analysed the smoothie produced! (Please note: that is not a safe activity for a home science practical.)
Allison Britt, Director of Mineral Resources Advice & Promotion, Geoscience Australia – at a live recording of 'Okham's razor'. (Source: Twitter)
As a science teacher (well, retired – but once a science teacher, always a science teacher at heart at least) I tend to be primed to focus on the ways in which teachers and scientists 'make the unfamiliar familiar', and Britt used an analogy with multiple targets.
The source domain was something familiar from everyday life – seasoning food.
I thought this worked really well, although as a purist (and, as noted here before, something of a pedant) I would have liked the third of her comparisons to refer to a difference that was a matter of degree (e.g., 'taste better' cf. 'work more efficiently'). That said, Britt's formulation worked better as scientific poetry:
So, just like adding salt and pepper to a meal makes it taste better:
putting a little rhenium in a jet engine makes it burn faster and hotter;
putting a little scandium in an aeroplane makes it lighter and stronger;
and putting a little indium in your mobile phone makes the touchscreen work.
Britt, 2021
This was an example of a science communicator making the point of how adding a small, sometimes trace, quantity of a substance can make a substantive difference to properties. I imagine that virtually everyone listening to this would have effortlessly understood the comparison – a key criterion for an effective teaching analogy.
