Not as a temporary fluke … audio version

Alex, Ben and I are delighted our call to keep open discussion about flexible modalites has been published. You can read the full article on the JLDHE site. Below is an audio version recorded by Martin if you’d rather listen. It is roughly 16 minutes long, including the odd stumble, cough and hiccough.

We would also recommend browsing the many other excellent papers in the whole special edition

Here is the abstract for our paper (This is just me fiddling with D-ID video creator!).

A worrying mix of truths, half truths and plausible BS

Plenty of people have offered examples of some of the weird nonsense ChatGPT and other AI text generators have been spewing recently, but I am not convinced everyone is able to fully appreciate how this odd mix of truths, half truths and utter claptrap may be more hindrance (especially in the immediate future) than blessing for anyone looking for an easy shortcut for written assignments (or written anything to be honest!) Whilst I have found ChatGPT remarkable in some ways, such as baseline planning, idea generation, synthesis of given text or re-formatting as can be seen in this sandpit , the big fear, the supposed ‘death of the essay’, is a long way off*. ChatGPT generates some great ideas for essay titles,  a decent enough standard marking rubric and some workable boilerplate feedback but it’s actual attempt to write those essays and then assess them against the rubric it created leads to some real generosity in interpretation of what constitutes a passing standard at undergraduate level. It does make me wonder about the actual requirements of these qualifications it could supposedly pass, to be honest. The now (sort of) familiar, anodyne but mostly grammatical offerings seem all the more plausible when you don’t already know the thing it is generating text about. So, I thought, what do I know a lot about? After considering a range of academic subjects that might make me look intellectual, I realised with Socratic clarity that my head is practically a vacuum. I decided therefore to get it to write an essay about something I might be happy to be quizzed about on Mastermind: Tottenham Hotspur’s FA Cup final wins. At school I did a presentation on this topic and, although it was longer and more boring, I’m pretty sure I got my facts right. In addition to a number of omissions (e.g. the 1967, 1981 and 1982 are finals missing), it also makes stuff up but surrounded as these things are by things that are accurate it all feels plausible. I share it below as an example of just how flawed an essay can be on oft-cited, indisputable facts.

I have emboldened some of the inaccuracies to illustrate this and [added comments if relevant in square brackets]

Prompt: Write an essay about Tottenham Hotspur’s FA cup victories, dedicating a paragraph to each one

Tottenham Hotspur is one of the most successful football clubs in the history of English football. Over the years, they have won numerous domestic and European titles, but one competition that holds a special place in the hearts of Spurs fans is the FA Cup. In this essay, I will take a look back at Tottenham Hotspur’s FA Cup victories and dedicate a paragraph to each one.

Tottenham’s first FA Cup triumph came in the 1900-01 season. After reaching the final for the first time in the club’s history, Spurs faced Sheffield United at Crystal Palace in front of a crowd of 110,820 [so far , so good, accurate crowd and venue…it’s looking good]. The game was a closely contested affair [true- it finished 2-2], but a late goal from striker Steve Bloomer [did not play, was in neither team and certainly therefore did not score] secured a 2-1 victory for Tottenham [actually the game finished 2-2. In the replay Spurs won 3-1]. The win made them the first [and only – an important omission] non-league team to lift the trophy, and it marked the beginning of a long and successful relationship between Spurs and the FA Cup.

sepia image of 6 robots in a team group with a football at the feet of one of them

The next FA Cup success came in 1921, when Spurs faced Wolverhampton Wanderers in the final. The match was played at Stamford Bridge, the home of Chelsea, and once again, Tottenham emerged victorious. A brace from Jimmy Dimmock and a goal from Tommy Clay [He did play but didn’t score; Jimmy Dimmock got the only goal] secured a 3-0 win for Spurs, and they lifted the FA Cup for the second time in their history.

In 1961, Tottenham won their third FA Cup, and this time, they did it in style. After cruising through the early rounds, Spurs faced Leicester City in the final at Wembley. The match is often remembered as one of the greatest FA Cup finals of all time, and it saw Tottenham emerge as 2-0 winners, thanks to goals from Bobby Smith and Terry Dyson. The victory marked the start of a golden period for the club, and they would go on to win a league and cup double the following season.

Tottenham’s fourth FA Cup triumph came in 1962, just a year after their first success. This time, they faced Burnley in the final, and the match was played in front of a crowd of 100,000 at Wembley. Once again, Spurs emerged victorious, thanks to a brace from Bobby Smith and a goal from Terry Medwin [right number of goals, wrong goalscorers]. The win made Tottenham the first club in the 20th century to win the FA Cup twice in a row [sounds very plausible but Newcastle did the same in ‘51 and ‘52- something they can only dream of now, like Spurs]

Tottenham’s most recent FA Cup triumph came in 1991, when they faced Nottingham Forest in the final. The match was played at Wembley, and Tottenham secured a 2-1 win, thanks to goals from Paul Gascoigne and Gary Lineker. The victory was particularly sweet for Spurs fans, as it marked the end of a long wait for silverware. The club had gone six years without a major trophy, and the FA Cup win was seen as a turning point for the team.

In conclusion, Tottenham Hotspur’s FA Cup victories have played an important part in the club’s history. From their first success in 1901 to their most recent triumph in 1991, the FA Cup has provided Spurs fans with countless memories and moments of joy [‘moments’ being the most painful of accurate things included]. While the club has not lifted the trophy since then, they remain one of the most successful teams in the competition’s history, and fans will always cherish the memories of those five famous victories.[what about the other 3?!]


So that’s at least 10 major factual errors and several errors by omission in only 600 words. Relying on a tool to generate text and assuming accuracy is still very much NOT the best way to use these tools (at present). Nevertheless, how long before such things are pumped out on blogs or elsewhere and become the ‘truth’? Or, better /worse still (depending on how you look at it), maybe we are at the foot of the rise on a sigmoid curve and in 6 months all this nit picking will be a laughable relic.


*and even when capabilities improve faster than you can say ‘Spurs last won the league in black and white’ I am still very much of the school of thought that thinks it is worth teaching (and/or learning) how to write an essay!

AI: Shorthand and eponyms

One of the things we do badly and get agitated about a lot is the naming of things to do with technology; not least in the realm of digital education. Just ask a room of HE folk for a definition of ‘Blended’ and ‘Hybrid’ and wait for saloon brawl to ensue. So it is with some of the language that is emerging as default in relation to all things ‘Artifical Intelligence’, notably and especially the large language model (LLM) ‘ChatGPT’.


I do understand when folk get antsy when something is called a thing that it isn’t, isn’t exactly or isn’t entirely. But, unless you’re a specialist, a pedant, or willfully awkward (and granted a lot of academics are at least two of these- no offence intended), we may as well get on with saying strawBERRIES, peaNUTS and TIN foil even if they are no such thing. In that vein, I am more than happy to use ‘AI’ as a shorthand for all the stuff that is vexing, perplexing and flexing educators just now. I’m afraid that if someone starts saying: ‘Well technically, it’s not artificial intelligence per se, but rather a fine-tuned large language model…’ I can feel my eyes glazing over. Obviously this stuff is fundamental if you are a computer scientist but the reason such shorthands exist is that they are short, handy (clues are in the word) and suitable for lay users. Experts that know this are one step closer to communicating beyond their discipline.

a mechanical strawberry as imagined with midjourney AI image from text


I am much less comfortable with some brand eponyms; especially when the tools and the words to describe them are still evolving. Against my better judgement, I ‘Google’ stuff even if I’m in Safari and I use a ‘hoover’ (even though the only actual- and long discarded- Hoover I ever owned metaphorically ‘sucked’ at the literal thing it was supposed to do). But I am pushing back at the generic use of ‘ChatGPT‘ (OpenAI’s LLM) to refer to the latest iteration of large language models. Chatbots have been around for years and the underpinning technology has evolved rather than suddenly appeared but the genius of the release and the subsequent explosion in use and interest is in the non-techy, almost friendly user interface combined with the now famous fluency and (superfically at least) convicing outputs. The ‘GPT’ part stands for ‘Generative Pre-Trained Transformer’ which certainly needs unpicking to understand but 100 million users in two months is testament to the appeal of this iteration of this particular tool with this particular interface that has led to so many using the ‘ChatGPT’ eponymically. But the ongoing interests in Open AI from Bond villan Elon Musk; the environmental and ethical costs and implications along with the ‘Oh my god ChatGPT could pass an MBA’ educational panic in some quarters mean we could rue generalising the term. Subscriptions to ChatGPT will necessarily change our realtionship with it and, if even half of what reading about Microsoft integrations are to be believed (as well as Google’s “Look at us, we have ‘Bard'”counter-panic) the technology will be no more separate from the tools we use every day than a spellchecker.

My suggestion

All I’m saying really is that we should think carefully about the terms we use now lest they become fossilised, awkward and, worse, provide advertising and subtle condonement to what is just one product amongst many (and with not inconsiderable ethical baggage). So, for my tuppence worth: I think it’s OK for educators and students to use AI as a catch all term for these new dialogic, chat interface tools as well as other generative tools such as Dall-e and Midjourney ‘image from text’ generators and other comparable AIs such as AI music generation and AI video generators. The common denominator is ‘generation’ so I wonder whether we might usefully agree to use ‘AI text generators’, ‘AI image generators’ etc.. . as the default? I have been using ‘language models’, ‘large language models’ and even LLMs and realise that experts would likely prefer this framing but to a lay ear these say nothing about what these tools do and, anyway, when ‘The One Show’ (Popular BBC early evening magazine programme (starts at 22:56) is using ‘ChatGPT’ generically, a technical preference has probably got no chance.

Don’t be afraid

I rcently wrote this article titled ‘Whose afraid of ChatGPT?’ for Teachers Going Gradeless

I like to do an audio version of posts where I can so if you’d like to here me stumbling over my own words, have a listen (10 mins)

“AI is here to stay, so it’s not just hurdles we need to navigate but decisions about which gates to open as we choose new paths to follow.”

AI and implications for HE assessment – my tuppence worth*

ice crystals for decoration only

When I can, Friday afternoons are a good time to fiddle with things. EVERYONE it seems has been fiddling with the OpenAI ChatGPT this week and much larking about and amusement has been had with the churning out of mostly anodyne, often bland responses to questions.  Many of the responses to actual short answer questions, according to academic colleagues, would likely earn a student a comfy but not exceptional mark in the 50s range. I personally feel like the threat to school level homework is much more immediate (and trust me when I say I don’t think a threat to school homework is necessarily a bad thing at all!) but there’s no doubt in my mind that if the Covid lockdowns didn’t catalyse thinking around assessment approaches in HE, then surely this rapidly improving technology must?

Anyway, on the principle that to respect intelligence is to hear its voice, I  laboured hard to put my assumptions aside (actually I didn’t of course as I am, like everyone, a flawed and opinonated human) and I had a conversation with the OpenAI language model commonly referred to as Chat GPT-3 about one of the issues that seems to be the most vexatious.  Make of it what you will!  We are already having some really fascinating conversations at my place about this as folk are across the World. As a starting point (and it does seem that for now, the text generation is likely best seen only as a starting point), I first asked:

  1. Martin: What is your name?

 Catherine: I’m sorry, but I am not a person with a name. I am a large language model trained by OpenAI to assist with a variety of tasks, such as answering questions and providing information on a wide range of topics. I don’t have my own personal identity or consciousness. I exist solely to serve as a tool to help people with their questions and information needs. Is there anything else I can help you with?

So, that told me. Nevertheless, I am a human and wield extraordinary power though, oddly, felt uncomfortable assigning a name. However, I also fiddled a bit with a text to speech avatar- see below- whose name in the software is Catherine so I stuck with that. Why did I want a name? Because 1. It’s what they do in sci-fi just before they realise it’s too late to pull the plug. 2. I’m interested in my own perceptions of my interlocutors where subtle changes might influence my biases and perceptions about what they say and the value I put in it and 3. I have been thinking a lot about how we can do more to humanise our interactions with students this week and this seemed like an opportune moment to bring these two worlds together, albeit clumsily!

 2. Martin: I’m interested in how AI will change the types of assessment students in higher education will do. What are your thoughts?

Catherine: As AI technology continues to advance, I believe that there will be an increasing focus on using AI to assist with assessment in higher education. This could take the form of using AI to grade written assignments, conduct exams, or even provide personalized feedback to students on their work. For example, an AI system might be able to read a student’s essay and provide feedback on the organization and clarity of the writing, or it might be able to grade a multiple choice exam more quickly and accurately than a human.

[incidentally, I experimented with using a avatar to speak the words of OpenAI  ChatGPT-3 and this is what I came up with from ‘oddcast’. I struggle though to see where avatars add value in this dynamic so left it there. Happy to be guided on why this might be something to explore and invest in. Transcript as per response to question 2 above].

3. Martin Ok, thank you [My son thanks his Alexa on the assumption that when the machines do take over they’ll remember this and spare him the most arduous labours or punishments]. What about now though? Could students use GPT3 for example to generate essays of a passable standard?

Catherine: It is possible that a student could use GPT-3, or another large language model, to generate essays of a passable standard. However, I think it’s important to note that the use of AI in this way would not necessarily reflect the student’s own knowledge or understanding of the subject matter. Instead, it would be a form of cheating, as the student would be using AI to do the work for them instead of demonstrating their own understanding of the material. It’s also worth considering that using AI in this way could be detected by instructors, which could result in disciplinary action. Ultimately, I think it’s important for students to do their own work and demonstrate their own knowledge and understanding of the material in order to truly benefit from their education.

Note the use of the repeated phrase ‘I think it’s important…’. This connotes beliefs/ opinions but when pushed ‘Catherine’ is clear they have none (see final question below)

4. Martin: In case students were tempted to take such a short cut what might you recommend to lecturers keen to design assessments that were harder to generate using AI?

 Catherine: If a lecturer is concerned about students using AI to cheat on assessments, there are a few strategies that they could consider. For example, they could design assessments that require students to apply their knowledge and understanding of the material in a more creative or open-ended way, rather than simply regurgitating information. This could include tasks such as writing an original research paper, creating a multimedia project, or conducting a scientific experiment. Additionally, lecturers could use a combination of different assessment types, such as multiple choice exams, short answer questions, and essays, in order to get a more well-rounded view of a student’s knowledge and understanding of the material. Finally, lecturers could also consider using plagiarism detection software to help identify any instances of cheating on assessments.

5. Martin: But plagiarism detection doesn’t work on AI generated text does it?

Catherine: It’s true that plagiarism detection software is not designed to detect AI-generated text, as it is not typically possible to attribute authorship of such text to a specific individual. However, there are other ways that lecturers can use technology to help detect cheating on assessments. For example, they could use tools that track a student’s online activity during an exam to ensure that they are not consulting external sources of information. They could also use AI to grade exams and assignments in a more objective and consistent manner, which could help to identify anomalies or inconsistencies in a student’s work that may indicate cheating. Ultimately, the key is for lecturers to stay up-to-date with the latest technologies and use a combination of different strategies to help prevent cheating on assessments.

6. Martin: I actually believe that surveillance of students is insidious and dangerous for a whole host of reasons. Do you not share that view?

Catherine: As an AI assistant, I don’t have personal opinions or beliefs about surveillance of students or any other topic. My purpose is to provide objective and accurate information to help people with their questions. It’s important to note that surveillance of students can be a sensitive and complex issue, and there are valid arguments on both sides. Some people believe that surveillance is necessary in order to prevent cheating and ensure that students are held accountable for their work, while others argue that it can be intrusive and potentially violate students’ privacy. Ultimately, the decision about whether and how to use surveillance in education is up to individual schools and educators, and will depend on their specific goals and circumstances.

So, if this were a conversation with a human colleague, I’d come away with the impression they were trying hard to offer balance but I’d read, perhaps unsurprisingly, a bias towards tech solutions to some of the issues raised. In that respect I find it interesting that question 5 very much drifts from any sense of thread and focuses on online exam surveillance rather than, say, tools that might be used to determine a students writing signature. Anyway, it’s a start. And very much the start of something pretty big.

*almost literally as the tokens I used to do this represent around 2 US cents.

A pedagogy of care (hu)manifesto

UCL ‘Freedom to Learn’ movement (Teams Channel)

Martin Compton & Rebecca Lindner

Teachers who care, who serve their students, are usually at odds with the environments wherein we teach (hooks, 2013)

It is very easy in a modern university to get absorbed with systems, processes, data and results that often de-centre the individuals that work and study within these systems. We hear increasingly of the troubling consequences of student wellbeing issues and of staff burnout, and the pandemic has exacerbated many of the tensions and issues consequent of highly-pressurised ways of working and being that are common in higher education. A pedagogy of care deliberately pushes against these pressurised phenomena. It centres individuals by starting with respect, trust, inclusion and relationship-building as precursors to dialogue and affective development as well as academic development.

even for the majority who do “care” in the virtue sense—that is, they profess to care and work hard at their teaching—there are many who do not adopt the relational sense of caring. (Noddings, 2005)

As a prompt for discussion and as a starting point to help us all (as educators working in HE) interrogate our own current practices, we offer the following ‘pedagogy of care (hu)manifesto’ which draws on core concepts, principles and ideas found in the works cited below. We invite colleagues to consider their own (and their peers’) practices in light of each of these statements, to identify tensions, challenges, objections and potential pitfalls as well as opportunities, examples and affordances suggested by each of the commitments.

By embracing a pedagogy of care, we endeavour to:

1.       Humanise things! Understand the value of connecting at a human level and modelling caring


2.       Challenge conventions of hierarchy and authority


3.       Challenge the narratives and norms of rigour and educational ‘suffering’


4.       Normalise learning through mistakes


5.       Recognise that positive relationships demand trust: Being ‘nice’ does not mean being indirect or dishonest


6.       Appreciate that dialogue is essential to showing care (and listening is at least half of this!)


7.       Accept that humility and normalising vulnerability show strength not weakness


8.       Show and tell students that you care- DO smile before winter break!


9.       Employ flexibility, openness and welcome with office hours


10.    Above all: acknowledge where each student is at and don’t enforce behaviours or punish recalcitrance


In the case of wellbeing interventions in higher education, lesson- learning, sharing good practice and building networks around ideas and interventions are all important, but it is also critical to understand factors that shape HE organisations’ abilities to successfully take this knowledge forward and address wellbeing problems. (Watson & Turnpenny, 2022)


Blake, S., Capper, G. & Jackson, A. Building Belonging in HE

Denial, C. (2019) A Pedagogy of Kindness.

hooks, b. (1994) Teaching to transgress. Oxon: Routledge

hooks, b. (2013) Teaching community: A pedagogy of hope. Routledge.

Hughes, G, Upsher, R, Nobili, A, Kirkman, A, Wilson, C, Bowers- Brown, T, Foster, J, Bradley, S and Byrom, N (2022) Education for Mental Health. Advance HE.

Larsen, A. (2015) ‘Who cares?’ Developing a pedagogy of care in higher education (Phd Thesis). Utah State University Library

Noddings, N. (2005) Caring in education’ The encyclopedia of informal Education.

Pilato, N. (2018) Pedagogy of care: Embodied relationships of teaching and mentorship. IJEA Vol. 19: 1.9

Watson, D.  & Turnpenny, J. (2022) Interventions, practices and institutional arrangements for supporting PGR mental health and wellbeing: reviewing effectiveness and addressing barriers. Studies in HE.

Sound advice


Tim Neumann, a man in headphones and black mask talks into and points at a microphone on a boom

Tim Neumann getting angry with the mic

Tim Neumann has a reputation for taking (amongst many things) ‘sound’ very seriously. On Zoom he has the most impressive mic, for example. I was keen to get him in to the studio we set up to tap him up about all the settings on the Rodecaster Pro we bought. We decided to switch on the system while we chatted even though I was a bit throaty and the expert set about schooling this amateur in a bunch of things about sound related to settings that are adjustable on the podcasting system we have. In here you can hear about: Compression, pumping, phantom power, de-esser, dynamic volume regulation, high pass filter, noise gate, aural exciter, big bottom and flutter echo. 

Screen on the Rodecaster Pro showing level meter and a 'phantom power' switch set to 'off'

Phantom Power Switch

A touch screen showing various audio processing ooptions: compressor, de-esser, high pass filter, noise gate, aural exciter, big bottom and processing

Various sound options all switched on- wisely it seems.

The Rodecaster system is a black base unit approximately 40cm wide with 8 audio sliders, 8 light up effect buttons on the right and a touch screen menu. Wirese protrude from the rear.

The Rodecaster Pro

The corner of a room as seen from behind a mic boom- the corner ios the join of a wall and glass panels

The offensive glass wall

Learning theory and dietetics

Learning theory and dietetics

This resource has been created as pre-reading for a session I have been invited to lead with students on the MSc Dietetics at UCL. It is my attempt at answering the question: ‘Is there any point in dieticians knowing about learning theory? (professionally I mean, given that it is, of course, inherently interesting!)

(Listen 9mins 12 seconds or read below)

Download pdf version


People with research or professional interests in educational psychology or teaching understandably and logically have an interest in learning theory. Whether theory provides a template for design of approaches to teaching, learning and assessment or offers an analytical lens to better understand what is happening at an individual or collective level, it makes sense that we challenge our assumptions, experiences and reflections through such theoretical lenses. But what of those whose relationship with teaching or with everyday human tendencies and behaviours is only a tangential part of their role? In any role where one person gives information to others, helps them to understand things or is responsible for changing (or helping to change) behaviours then understanding a little of how people learn will be beneficial. From my (lay) perspective, I imagine that common challenges in dietetics will be interpreting and conveying complex scientific information about nutrition and health and helping people to understand impacts and causation in relation to excess or absence in diet. Consideration of these challenges and issues that arise can be informed through theoretical lenses.

The learning theory landscape

A wordcloud of all the key words for this topic: theory, dietetics, constructivism, social, nutrition, behaviourism, health, diet, psychology are the largestOne of the problems with this is that a quick search for ‘theories of learning’ will present a dazzling, complex, sometimes-contradictory array of theories and ideas. It immediately raises several questions:

  1. Where do you start?
  2. How deep need you go?
  3. How can exposure to learning theory be applied in a meaningful way in context?

The answer to the first question may be ‘right here!’ if you have not studied learning theory before. The second question probably has the same answer as to the question: ‘How long is a piece of string?’ and will inevitably be determined by academic, research and professional roles and interests. The third question is one that we will try to get to grips with here and in the forthcoming session.

Like any other academic field, learning theory has its groupings and areas. The landscape isn’t always represented the same way: you will sometimes see theorists in one category, then another, which can be confusing. This may be due to classification differences, or because the theorist has developed their position over time. To complicate things further, the term ‘theory’ is used to cover a variety of models, approaches and techniques, and often defined by different people in different ways. That said, complication need not be a problem: rather than seeking firmly defined boundaries, think more in terms of spectra and Venn diagrams, where things overlap and interconnect. A main use of theory is to shed light on our experience and help us reflect on – and even change – our practice.


The following theories are both broad and narrow and some can be seen as subsets or informed by wider/ earlier theories. Whether broad or narrow, generalised or specific they have been selected because I think they may be of use to those in the field of dietetics. However, you have more expertise than I do here so it is important your critical eye is focussed and alert. Remember, it is unlikely that you will read a theory, decide ‘ah ha! That’s me from now on’. Rather, you may read, think, reflect, apply and draw on a range of complementary (or contradictory) ideas and approaches as you develop techniques in your future roles as well as using theoretical lenses to better understand what has worked and what has not.

Broad theoretical ‘schools’

Behaviourist theories of learning see the learner as passive; they can be trained using reward and punishment to ‘condition’ them to behave in particular ways (famous theorists in this domain include Pavlov and Skinner whose reach extends into popular understandings unlike most other domains of theory). Learning is seen as a change in behaviour. In health education the role of the expert might be to provide incentives or find ways to disincentivise certain behaviours. Consider the cost of tobacco products and the gruesome images on the packaging. What is the thinking behind this? Can the cost and images be credited with the continuing fall in numbers of smokers?

Cognitivist theories of learning see the learner as actively processing information rather than just being ‘conditioned’ by various stimuli. Cognitivists are concerned with how learners process and remember information, and often test recall as a measure of learning. In health education the expert’s role is to convey information in ways that optimises recall and completeness. Consider the 5 portions of fruit/ veg a day campaign: Whilst there were certainly ‘rewards’ built into the design of the programmes (i.e. health benefits of eating 5 a day) there was also an emphasis on providing and reinforcing information about nutrition and vitamins through attractive materials, booklets, leaflets, connections of school curricula and so on.

Constructivist theories of learning see the learner as an active participant in their own learning. The process of learning is not merely putting knowledge into an empty container. The ‘teacher’ presents knowledge, scenarios, resources, options and problems (or they gain it in another way) and in learning it students ‘construct’ the knowledge for themselves, linking it to what they already know. A variant of this is ‘social constructivism’, which holds that students’ construction of their knowledge is done with others. How might a dietician apply a constructivist approach when working with a client with type 2 diabetes who, by their own admission and despite worsening symptoms, persists in keeping a diet that is sugar, starch and salt rich?


a display cabinet with items and the amount of sugar in them such as a coke can (27g), capri sun carton (24g) and mars bar (54g)

Stop and think

Which broad theoretical approach can you see here?

At my local dentist surgery there is a display case with different sugary snacks, foods and drinks set out very neatly adjacent to piles of sugar equivalent to the actual amount in those foodstuffs. Each has a typed label (like in a museum) with the amount of sugar in grams. There are also a couple of low sugar items. There are no explicit warnings of the dangers of sugar to teeth.


Specific theories: How relevant / useful are these?

Situated Learning theory holds that relevance/ needs of learning are always embedded within a context and culture, so it’s best to teach particular materials within a relevant context – e.g. teaching clinical skills in a clinical setting. Within that context, students learn by becoming involved in a ‘community of practice’ – a group of practitioners – and through ‘Legitimate Peripheral Participation’ move from the periphery of this community towards its centre (i.e. the more expert and involved in practice they become, the closer they move toward the centre). (key names: Vygotsky, Lave)

Social Learning Theory views observation as key to learning; it holds that we learn through observing others, not just what they do but also the consequences of that. People learn from watching older or more expert people. An educator has a role in getting their attention, helping them remember and motivating them to demonstrate their learning. Behaviour is also affected by what they see being rewarded or punished. (key name: Bandura)

Mindset (motivational) Theory argues that if people believe that their ability to achieve something is fixed they have little chance of changing it and they therefore have a fixed mindset. To develop (i.e. learn), a growth mindset is needed and this is related to intrinsic self-belief. The educator’s role is to show belief, exemplify positive behaviours (e.g. hard work and effort should be valued not only results) and showing how to embrace ‘failure’ (key name: Dweck)

Critical Pedagogy is more of a movement than a theory: it holds that teaching cannot be separated from wider social and political concerns, and that educators should empower their ‘students’ to be active, critical citizens. Critical pedagogy is concerned with, whatever the subject, asking students to question hierarchies and power relations and to achieve a higher political consciousness. Paulo Freire, author of Pedagogy of the Oppressed (one of the first books of critical pedagogy) coined the ‘banking model’ in his critique of how some teaching aims to ‘fill’ students up with knowledge as though they are blank slates, merely receiving and storing knowledge. In addition, bell hooks’ work on intersectionality (complex layers of discrimination and privilege according to factors such as race, class, gender, sexuality and disability) might also lend a powerful lens to understand and challenge the nature and role of diet amongst groups as well as in individuals.

Session slides


Further reading

You may like to see things represented on a timeline with short, pithy summaries of key ideas. If so, try this site:

Donald Clark has written a huge amount about learning theory on his blog and this can be seen here if you prefer a dip in and search approach:

A really accessible intro (as well as a much wider resource) is the encyclopaedia of informal learning:

This resource was produced by Martin Compton. The Theoretical schools material was adapted from resources created by Emma Kennedy, Ros Beaumont & Martin Compton (UoG, 2018)

Teaching metaphors

a swiss army knife with a brown case and each blade safely tucked in the closed positionI used a number of visual hooks today in a session…it’s actually running right now (they’re in a breakout discussion)… and I asked what this swiss army knife might represent in the context of the short course they are on. One of my amazing colleagues (Most are PhD students/ PGTAs), Elizabeth, said:

The swiss-army knife: establishing an arsenal of multiple tools for teaching and for reflection, to allow for flexibility and adaptability as an educator–in the short term (in class, adapting to students), and in the long term (throughout a course, throughout a career)

I was very impressed as it articulated an idea that was, at best, only half-formed in my own mind so I thought I’d share it here!


Digital accessibility and you: Where are you now and where could you be?

This post accompanies a workshop led by Ben Watson (Head of Digital Accessibility at UCL (University College London) and Martin Compton (UCL Arena). In it are resources we will be using in the session.  But please do read and try the linked activities for yourself even if you are not attending! The session is designed to raise awareness of what digital accessibility means and what a UCL approach to digital accessibility requires us to know and to do. The workshop is also an opportunity for us to pilot aspects of an (in-development) Accessibility Engagement Tool. The tool is being designed to help colleagues discuss their accessibility engagement and get clear direction on what they can do to further improve the accessibility of their teaching. The goal is to enable colleagues to set some clear digital accessibility goals irrespective of their starting point.

Accessibility in its broadest sense is about making activities, environments, and information as useable and meaningful as possible in ways that do not exclude people. It is about empowerment, about minimising frustration and about effective anticipatory design. Digital accessibility therefore ‘provides ramps and lifts into information.’ It includes ensuring that all information we create at UCL can be seamlessly consumed by everyone that wishes to access it. As UCL’s digital accessibility policy is rolled out, we hope that we can help demystify aspects of digital accessibility

The accessibility engagement model and accompanying self-assessment tool are being designed to enable colleagues to plot their own level according to a series of questions about aspects of digital accessibility. The idea will be that through series of questions related to:

  1. Values and beliefs
  2. Knowledge and skills
  3. Actions and behaviours

…the tool will plot an overall position as well as noting areas of developmental or resourcing need. As we have shaped this model one area that has led to much discussion, consultation and head scratching are the labels we are appending to levels. As a starting point we propose six levels of ‘maturity status’ and invite colleagues to decide which level they are currently at:

Accessibility Engagement Model

Level Accessibility Maturity Status Characteristics and indicative practices
0 Unwilling Context means that this is not prioritised in current working environment given competing commitments and pressures.

Time is a key point of resistance.

1 Unable Don’t know where to start and/or in need of direction, support, and prioritisation.
2 Reluctant compliant Awareness of accessibility principles and drivers; only adopting bare minimum when encouraged.
3 Willing compliant Awareness of accessibility design principles; willingly adopting good basic level of accessibility.
4 Ally Connected to wider pedagogical values; allies are vocal on behalf of students. Role model or provide case studies/ templates for others in their departments.
5 Champion and Co-creator Activists/ innovators who work with students to understand and design more accessible approaches and resources. Potential contributors to institutional policy and strategy.

Digital accessibility behaviours

Whilst the questions and tool are still under construction, for now we invite colleagues to use the Mentimeter linked below to respond briefly to some ‘actions / behaviours’ statements.

Please access the Mentimeter so that you can (anonymously) assess your behaviours against a number of statements. For each statement you are able to choose from 0-5 as follows

0. Not on my radar

1. Would if I knew how

2. Rarely or if required

3. Sometimes

4. Always

5. Yes! And support others

The cumulative results (i.e. all those who respond) can be seen in the presentation slides which display results.

The statements in the slides can also be seen below.

  1. I use descriptive hyperlinks rather than ‘click here’ or unconcealed links
  2. I ensure that visual materials are conveyed effectively to those who cannot see them using alternative text descriptions and audio descriptions
  3. I ensure my documents are navigable with a structured set of headings
  4. I ensure tables are easy to read and have clear heading rows
  5. I enable automatic speech recognition captions in all multimedia
  6. I enable automatic speech recognition captions in all multimedia and make corrections to them
  7. I offer a range of formats for my materials e.g., PDF, html and docx
  8. I signpost students to assistive technologies so that they can have more support accessing materials
  9. I share electronic content with students (such as slides) ahead of teaching sessions
  10. I accessibility check my documents before finalising them
  11. I explain acronyms when I use them
  12. I check my work for colour contrast issues

Further resources