Wellbeing in ELT: a Status Report

When I last blogged about teacher wellbeing in August 2020, we were in the early throes of COVID, and Sarah Mercer and Tammy Gregersen had recently published their timely book about wellbeing (Mercer & Gregersen, 2020). Now, over two years later, it seems appropriate to take another look at the topic, to evaluate the status of the concept of ‘wellbeing’ in ELT.

Wellbeing as an object of study

The first thing to be said is that wellbeing is doing just fine. Since 1995, the frequency of use of ‘subjective well-being’ in books has increased by a factor of eight, and, across multiple languages, academic attention to wellbeing and related concepts like ‘happiness’ is growing (Barrington-Leigh, 2022). Interest in teacher wellbeing is no exception to this trend. There are, however, a few problems, according to a recent systematic review of the research literature (Hascher & Waber, 2021). There is, apparently, little consensus on how the term should be defined. There is little in the way of strong evidence that wellbeing correlates with good teaching, and, to my surprise, there is a lack of studies pointing to actual shortfalls in teacher wellbeing. Empirical evidence regarding the effectiveness of programmes aiming to foster teacher wellbeing is, less surprisingly, scarce.

Researchers in English language teacher wellbeing are well aware of all this and are doing their best to fill in the gaps. A ‘research group for wellbeing in language education’ has recently been formed at the University of Graz in Austria, where Sarah Mercer works. This is part of a push to promote positive psychology in language teaching publications, and the output of Sarah Mercer, Tammy Gregersen and their associates has been prodigious.

Next year will see the publication of a book-length treatment of the topic with ‘Teacher Well-Being in English Language Teaching An Ecological Approach’ (Herrera et al, 2023). It will be interesting to see to what extent teacher wellbeing is dealt with as a social or political issue, as opposed to something amenable to the interventions of positive psychology.

In the wider world of education, wellbeing is not as frequently seen through the lens of positive psychology as it is in ELT circles. Other perspectives exist: a focus on working conditions or a focus on mental health, for example (Hascher & Waber, 2021). And then there is neuroscience and wellbeing, which I am eagerly awaiting an ELT perspective on. I have learnt that certain brain patterns are related to lower well-being (in the medial prefrontal cortex, posterior cingulate cortex/ praecuneus, and angular gyrus areas, to be gratuitously specific). Lower wellbeing correlates with patterns that are found when the brain is at wakeful rest, such as during daydreaming and mind-wandering (Bartels et al. 2022). All of which sounds, to me, like a strong argument for mindfulness practices. Keep your eye out for ELT publishers’ webinars (see below) and you’ll no doubt hear someone taking this line, along with some nice fMRI images.

Wellbeing and self-help

Academic study of wellbeing proceeds apace, but the ultimate justification for this research can only be found in its ability to help generate solutions to a real-world problem. In this sense, it is no different from the field of applied linguistics in general (from where most of the ELT wellbeing researchers come): it is its ability to solve problems which ‘alone justifies its existence in the first place’ (Widdowson, 2018: 142).

But here we run into something of a brick wall. Whilst it is generally acknowledged that improvements to teacher wellbeing require ‘structural and systemic levels of change’ and that ‘teachers should not have to compensate for fundamental flaws in the system as a whole’ (Mercer & Gregersen, 2020: 9), the ‘solutions’ that are proposed are never primarily about systems, but always about ‘me’. Take a look at any blog post on teacher wellbeing in ELT and you will see what could be called the psychologizing of the political. This process is at the heart of the positive psychology movement which so dominates the current world of wellbeing in ELT.

A look at the Teacher Wellbeing SIG of BRAZ-TESOL (on Facebook or Instagram) gives a good sample of the kind of advice that is on offer: write out a self-appreciation list, respect others, remember you are unique, be grateful, smile, develop emotional intelligence and a growth mindset, start with yourself, take care of yourself, look after your ‘authentic self’, set goals, believe that nothing is impossible, take small steps, pause and breathe, spend time with positive people, learn to say no, and so on. This advice is offered in all seriousness, but is not so very different from the kind of advice offered by @lifeadvicebot on Twitter (‘Are you struggling with the impact of sexism? Consider cultivating a sense of gratitude’ or ‘Worried about racism? Why not try stretching your back and shoulders?).

I don’t mean to suggest that mindfulness and the other nostrums on offer will be of no benefit to anybody at all, but, however well-intentioned such advice may be, it may be ‘rather better for its promoters than for its putative beneficiaries’ (Widdowson, 2021: 47). The advice is never new or original. It is rutted with the ‘grooves of borrowed thought’, lifting directly from the long tradition of self-help literature, of which it is yet another exemplar. Like all self-improvement literature, you don’t need any deep commitment to read it. Written in an accessible style (and in the case of the BRAZ-TESOL SIG in the form of illustrated inspirational quotes), there is a slight problem with all this advice. If you do decide to dive into it repeatedly, you will quickly discover ‘that it is not such a long way from surface to bottom’ (Lichterman, 1992: 427). Like all self-help literature, as Csikszentmihalyi (1990) observed on the back cover of his best-selling work, it will probably have no effect whatsoever. Whether you agree with Csikszentmihalyi or not, there is a delicious irony in the fact that this comment appeared on the back cover of his own self-help book. Like all positive psychologists, he thought he had something new and scientifically grounded to say.

There are also increasing numbers of wellbeing coaches – a thoroughly unsurprisingly development. Many of them are positive psychology adepts, some describe themselves as neuro-science based, and have a background in Neuro-Linguistic Processing. In the context of education, expect the phrase ‘life skills’ to be thrown in from time to time. See this article from Humanising Language Teaching as an example.

But self-help literature treads familiar ground. Work on the self may seem like ‘an antidote to the anxiety-provoking uncertainties of [our] economic and social order’ (McGee, 2005: 43), but it has nowhere to go and is doomed to follow its Sisyphean path. If research into teacher wellbeing in ELT cannot shake off its association with positive psychology and self-help, its justification (and interest in it) will soon slip away.

Wellbeing as a marketing tool

Wellbeing is ideally positioned as a marketing trope … as long as the connections between low wellbeing and pay / working conditions are not dwelled on. It’s a ‘new’ and ‘virtuous’ topic that sits comfortably beside inclusivity, sustainability and environmental awareness. Teaching is a caring profession: a marketing focus on wellbeing is intended to be taken as a sign that the marketers care too. They have your best interests at heart. And when the marketing comes in the form of wellbeing tips, the marketers are offering for free something which is known to be appreciated by many teachers. Some teacher wellbeing books, like the self-published ‘The Teacher’s Guide to Self-Care: Build Resilience, Avoid Burnout, and Bring a Happier and Healthier You to the Classroom’ (Forst, 2020), have sold in considerable quantities.

BETT, which organises a global series of education shows whose purpose is to market information technology in education, is a fascinating example of wellbeing marketing. The BETT shows and the website are packed with references to wellbeing, combining the use of wellbeing to market products unrelated to wellbeing, at the same time as marketing wellbeing products. Neat, eh? Most of these uses of ‘wellbeing’ are from the last couple of years. The website has a wellbeing ‘hub’. Click on an article entitled ‘Student Wellbeing Resources’ and you’ll be taken to a list of products you can buy. Other articles, like ‘Fostering well-being and engagement with Microsoft education solutions’, are clearer from the get-go.

All the major ELT publishers have jumped on the bandwagon. Some examples … Macmillan has a ‘wellness space’ (‘a curated playlist of on-demand webinars and practical resources to specifically support your well-being – and for you to return to as often as you like’). They were also ‘delighted to have championed mindfulness at the IATEFL conference this year!’ Pearson has a ‘wellbeing zone’ – ‘packed with free resources to support teachers, parents and young people with mental health and wellbeing – from advice on coping with anxiety and exam stress, to fun activities and mindfulness’. Last year, Express Publishing chose to market one of its readers with the following introductory line: ‘#Reading for pleasure improves #empathy, #socialrelationships and our general #wellbeing’. And on it goes.

Without going as far as to say that these are practices of ‘wellbeing washing’, it is only realistic, not cynical, to wonder just how seriously these organisations take questions of teacher wellbeing. There are certainly few ELT writers who feel that their publishers have the slightest concern about their wellbeing. Similarly, we might consider the British Council, which is ‘committed to supporting policymakers, school leaders and teachers in improving mental wellbeing in schools’. But less committed, it would seem, to their own teachers in Kabul or to their staff who went on strike earlier this year in protest at forced redundancies and outsourcing of jobs.

How long ‘wellbeing’ will continue to be seen as a useful marketing trope in ELT remains to be seen. It will be hard to sustain for very long, since there is so little to say about it without repetition, and since everyone is in on the game. My guess is that ‘wellbeing’ will soon be superseded by ‘sustainability’. ‘Sustainability’ is a better hooray word than ‘wellbeing’, because it combines environmental quality and wellbeing, throwing in ‘lifelong learning’ and ‘social justice’ for good measure (Kapranov, 2022). The wellbeing zones and hubs won’t need to be dismantled just yet, but there may well be a shift towards more sustainable self-care. Here are some top tips taken from How To Self-Care The Sustainable Way on the Wearth website: snooze your way to wellbeing, indulge and preen your body, grab a cuppa, slip into a warming bath, mindfully take care of your mind, retail therapy the wholesome way. All carbon-neutral, vegan and cruelty-free.

References

Barrington-Leigh, C. P. (2022) Trends in Conceptions of Progress and Well-being. In Helliwell, J. F., Layard, R., Sachs, J. D., De Neve, J.-E., Aknin, L. B. & Wang, S. World Happiness Report 2022. https://happiness-report.s3.amazonaws.com/2022/WHR+22.pdf  New York: Sustainable Development Solutions Network.

Bartels, M., Nes, R. B., Armitage, J. M., van de Weijer, M. P., de Vries L. P. & Haworth, C. M. A. (2022) Exploring the Biological Basis for Happiness. In Helliwell, J. F., Layard, R., Sachs, J. D., De Neve, J.-E., Aknin, L. B. & Wang, S. World Happiness Report 2022. https://happiness-report.s3.amazonaws.com/2022/WHR+22.pdf  New York: Sustainable Development Solutions Network.

Csikszentmihalyi, M. (1990) Flow: The Psychology of Optimal Experience. New York: Harper & Row

Forst, S. (2020) The Teacher’s Guide to Self-Care: Build Resilience, Avoid Burnout, and Bring a Happier and Healthier You to the Classroom. The Designer Teacher, LLC

Hascher, T. & Waber, J. (2021) Teacher well-being: A systematic review of the research literature from the year 2000–2019. Educational Research Review, 34 https://www.sciencedirect.com/science/article/pii/S1747938X21000348

Kapranov, O. (2022) The Discourse of Sustainability in English Language Teaching (ELT) at the University of Oxford: Analyzing Discursive Representations. Journal of Teacher Education for Sustainability, 24 (1):35-48 https://sciendo.com/article/10.2478/jtes-2022-0004

Pentón Herrera, L. J., Martínez-Alba, G. & Trinh, E. (Eds.) (2023) Teacher Well-Being in English Language Teaching: An Ecological Approach. Abingdon: Routledge

Lichterman, P. (1992) Self-help reading as a thin culture. Media, Culture and Society, 14: 421 – 447

McGee, M. (2005) Self-Help, Inc. Oxford: OUP

Mercer, S. & Gregersen, T. (2020) Teacher Wellbeing. Oxford: OUP

Widdowson, H. G. (2018) Applied linguistics as a transdisciplinary practice: What’s in a prefix? AILA Review, 31 (1): 135- 142

Widdowson, H. G. (2021) On the Subject of English. Berlin: De Gruyter

How to write about AI in language learning

The paragraph above was written by an AI-powered text generator called neuroflash https://app.neuro-flash.com/home which I told to produce a text on the topic ‘AI and education’. As texts on this topic go, it is both remarkable (in that it was not written by a human) and entirely unremarkable (in that it is practically indistinguishable from hundreds of human-written texts on the same subject). Neuroflash uses a neural network technology called GPT-3 – ‘a large language model’ – and ‘one of the most interesting and important AI systems ever produced’ (Chalmers, 2020). Basically, it generates text by predicting sequences of words based on huge databases. The nature of the paragraph above tells you all you need to know about the kinds of content that are usually found in texts about AI and education.

Not dissimilar from the neuroflash paragraph, educational commentary on uses of AI is characterised by (1) descriptions of AI tools already in use (e.g. speech recognition and machine translation) and (2) vague predictions which invariably refer to ‘the promise of personalised learning, adjusting what we give learners according to what they need to learn and keeping them motivated by giving them content that is of interest to them’ (Hughes, 2022). The question of what precisely will be personalised is unanswered: providing learners with optimal sets of resources (but which ones?), providing counselling services, recommendations or feedback for learners and teachers (but of what kind?) (Luckin, 2022). Nearly four years ago, I wrote https://adaptivelearninginelt.wordpress.com/2018/08/13/ai-and-language-teaching/ about the reasons why these questions remain unanswered. The short answer is that AI in language learning requires a ‘domain knowledge model’. This specifies what is to be learnt and includes an analysis of the steps that must be taken to reach that learning goal. This is lacking in SLA, or, at least, there is no general agreement on what it is. Worse, the models that are most commonly adopted in AI-driven programs (e.g. the deliberate learning of discrete items of grammar and vocabulary) are not supported by either current theory or research (see, for example, VanPatten & Smith, 2022).

In 2021, the IATEFL Learning Technologies SIG organised an event dedicated to AI in education. Unsurprisingly, there was a fair amount of input on AI in assessment, but my interest is in how AI might revolutionize how we learn and teach, not how we assess. What concrete examples did speakers provide?

Rose Luckin, the most well-known British expert on AI in education, kicked things off by mentioning three tools. One of these, Carnegie Learning, is a digital language course that looks very much like any of the ELT courses on offer from the big publishers – a fully blendable, multimedia (e.g. flashcards and videos) synthetic syllabus. This ‘blended learning solution’ is personalizable, since ‘no two students learn alike’, and, it claims, will develop a ‘lifelong love of language’. It appears to be premised on the idea of language learning as optimizing the delivery of ‘content’, of this content consisting primarily of discrete items, and of equating input with uptake. Been there, done that.

A second was Alelo Enskill https://www.alelo.com/about-us/ a chatbot / avatar roleplay program, first developed by the US military to teach Iraqi Arabic and aspects of Iraqi culture to Marines. I looked at the limitations of chatbot technology for language learning here https://adaptivelearninginelt.wordpress.com/2016/12/01/chatbots/ . The third tool mentioned by Luckin was Duolingo. Enough said.

Another speaker at this event was the founder and CEO of Edugo.AI https://www.edugo.ai/ , an AI-powered LMS which uses GPT-3. It allows schools to ‘create and upload on the platform any kind of language material (audio, video, text…). Our AI algorithms process and convert it in gamified exercises, which engage different parts of the brain, and gets students eager to practice’. Does this speaker know anything about gamification (for a quick read, I’d recommend Paul Driver (2012)) or neuroscience, I wonder. What, for that matter, does he know about language learning? Apparently, ‘language is not just about words, language is about sentences’ (Tomasello, 2022). Hmm, this doesn’t inspire confidence.

When you look at current uses of AI in language learning, there is very little (outside of testing, translation and speech ↔ text applications) that could justify enthusiastic claims that AI has any great educational potential. Skepticism seems to me a more reasonable and scientific response: de omnibus dubitandum.

Education is not the only field where AI has been talked up. When Covid hit us, AI was seen as the game-changing technology. It ‘could be deployed to make predictions, enhance efficiencies, and free up staff through automation; it could help rapidly process vast amounts of information and make lifesaving decisions’ (Chakravorti, 2022). The contribution of AI to the development of vaccines has been huge, but its role in diagnosing and triaging patients has been another matter altogether. Hundreds of predictive tools were developed: ‘none of them made a real difference, and some were potentially harmful’ (Heaven, 2021). Expectations were unrealistic and led to the deployment of tools before they were properly trialled. Thirty months down the line, a much more sober understanding of the potential of AI has emerged. Here, then, are the main lessons that have been learnt (I draw particularly on Engler, 2020, and Chakravorti, 2022) that are also relevant to education and language learning.

• Anticipate what could go wrong before anticipating what might go right. Engler (2020) writes that ‘a poorly kept secret of AI practitioners is that 96% accuracy is suspiciously high for any machine learning problem’. In language learning, it is highly unlikely that personalized recommendations will ever reach anything even approaching this level of reliability. What are the implications for individual learners whose learning is inappropriately personalised?
• We also know that a significant problem with AI systems is bias (O’Neil, 2016). There is a well-documented history of discriminatory outcomes because of people’s race, gender, social class or disability profile. Bias needs to be addressed proactively, not reactively.
• Acknowledge from the outset that, for AI to work, huge amounts of data related to prior outcomes will be needed. In the cases of both Covid and language learning, much of this data will be personal. This raises immediate questions of privacy and consent, especially for learners who are children. Don’t minimise this issue.
• Common by-products of AI use include insecure data storage, digital surveillance and consolidation of market power (Engler, 2020). Since such issues are so pervasive, assume they will be a problem, and need to be considered in evaluating the potential of any piece of AI edtech.
• Find out what the subject matter experts have to say: ‘AI is only helpful when applied judiciously by subject-matter experts—people with long-standing experience with the problem that they are trying to solve […] Effectively predicting a badly defined problem is worse than doing nothing at all’ (Engler, 2020). It may be that the problem the AI is trying to help solve is the wrong problem and not worth solving at all (e.g. more efficient ‘delivery’ of explicit grammatical knowledge, gamifying gapfills).

To bring this post to an end, I returned to the AI / GTP-3 driven neuroflash program. This time, I asked it to write a longer piece entitled ‘The dangers of artificial intelligence in education: what could go wrong?’. Here’s what it came up with:

There are a few potential dangers of artificial intelligence in education. One is that AI could be used to replace human teachers. This could lead to a decline in the quality of education, as machines are not yet capable of replicating the full range of human emotions and social interactions that are necessary for teaching. Additionally, AI could be used to create biased or “racist” educational materials, as has already happened with some commercial software products. Finally, AI could be used to track and monitor students in ways that invade their privacy, or that could be used to manipulate their behavior.

All of these dangers are real and should be taken seriously. However, it’s important to remember that AI is still a new technology, and its impact on education is not yet fully understood. As such, we should tread cautiously when implementing AI into our educational systems.

When it comes to education, artificial intelligence could be a double-edged sword. While AI has the potential to revolutionize the field of education and help students learn in more efficient ways, there are also dangers that need to be considered.

One of the dangers of AI in education is that it could lead to a more standardized and homogenized form of learning. If all students are relying on AI-based learning tools, they may all end up learning the same things in the same way. This could lead to a loss of creativity and individuality in education.

Another danger is that AI-based learning tools could become too reliant on data and algorithms. This could lead to a situation where students are simply being taught what the machines think they should know, rather than being allowed to explore and discover new things for themselves.

Finally, there is the danger that AI could eventually replace human teachers altogether. While this may seem like a far-fetched scenario, it is not outside the realm of possibility. If AI-based learning tools become sophisticated enough, they may one day be able to do the job of teaching just as well as humans can.

These are just some of the dangers that need to be considered when it comes to artificial intelligence in education. While AI has the potential to revolutionize education, we need to be careful about how we implement it so that we don’t end up doing more harm than good.

References

Chakravorti, B. (2022) Why AI Failed to Live Up to Its Potential During the Pandemic. Harvard Business Review March 17,2022. https://hbr.org/2022/03/why-ai-failed-to-live-up-to-its-potential-during-the-pandemic

Chalmers, D. (2020) Weinberg, Justin (ed.). “GPT-3 and General Intelligence”. Daily Nous. Philosophers On GPT-3 (updated with replies by GPT-3) July 30, 2020. https://dailynous.com/2020/07/30/philosophers-gpt-3/#chalmers

Driver, P. (2012) The Irony of Gamification. In English Digital Magazine 3, British Council Portugal, pp. 21 – 24 http://digitaldebris.info/digital-debris/2011/12/31/the-irony-of-gamification-written-for-ied-magazine.html

Engler, A. (2020) A guide to healthy skepticism of artificial intelligence and coronavirus. Washington D.C.: Brookings Institution https://www.brookings.edu/research/a-guide-to-healthy-skepticism-of-artificial-intelligence-and-coronavirus/

Heaven, W. D. (2021) Hundreds of AI tools have been built to catch covid. None of them helped. MIT Technology Review, July 30, 2021. https://www.technologyreview.com/2021/07/30/1030329/machine-learning-ai-failed-covid-hospital-diagnosis-pandemic/

Hughes, G. (2022) What lies at the end of the AI rainbow? IATEFL LTSIG Newsletter Issue April 2022

Luckin, R. (2022) The implications of AI for language learning and teaching. IATEFL LTSIG Newsletter Issue April 2022

O’Neil, C. (2016) Weapons of Math Destruction. London: Allen Lane

Tomasello, G. (2022) Next Generation of AI-Language Education Software:NLP & Language Modules (GPT3). IATEFL LTSIG Newsletter Issue April 2022

VanPatten, B. & Smith, M. (2022) Explicit and Implicit Learning in Second Language Acquisition. Cambridge: Cambridge University Press

Words & Monsters: a review

NB This is an edited version of the original review.

Words & Monsters is a new vocabulary app that has caught my attention. There are three reasons for this. Firstly, because it’s free. Secondly, because I was led to believe (falsely, as it turns out) that two of the people behind it are Charles Browne and Brent Culligan, eminently respectable linguists, who were also behind the development of the New General Service List (NGSL), based on data from the Cambridge English Corpus. And thirdly, because a lot of thought, effort and investment have clearly gone into the gamification of Words & Monsters (WAM). It’s to the last of these that I’ll turn my attention first.

WAM teaches vocabulary in the context of a battle between a player’s avatar and a variety of monsters. If users can correctly match a set of target items to definitions or translations in the available time, they ‘defeat’ the monster and accumulate points. The more points you have, the higher you advance through a series of levels and ranks. There are bonuses for meeting daily and weekly goals, there are leaderboards, and trophies and medals can be won. In addition to points, players also win ‘crystals’ after successful battles, and these crystals can be used to buy accessories which change the appearance of the avatar and give the player added ‘powers’. I was never able to fully understand precisely how these ‘powers’ affected the number of points I could win in battle. It remained as baffling to me as the whole system of values with Pokemon cards, which is presumably a large part of the inspiration here. Perhaps others, more used to games like Pokemon, would find it all much more transparent.

The system of rewards is all rather complicated, but perhaps this doesn’t matter too much. In fact, it might be the case that working out how reward systems work is part of what motivates people to play games. But there is another aspect to this: the app’s developers refer in their bumf to research by Howard-Jones and Jay (2016), which suggests that when rewards are uncertain, more dopamine is released in the mid-brain and this may lead to reinforcement of learning, and, possibly, enhancement of declarative memory function. Possibly … but Howard-Jones and Jay point out that ‘the science required to inform the manipulation of reward schedules for educational benefit is very incomplete.’ So, WAM’s developers may be jumping the gun a little and overstating the applicability of the neuroscientific research, but they’re not alone in that!

If you don’t understand a reward system, it’s certain that the rewards are uncertain. But WAM takes this further in at least two ways. Firstly, when you win a ‘battle’, you have to click on a plain treasure bag to collect your crystals, and you don’t know whether you’ll get one, two, three, or zero, crystals. You are given a semblance of agency, but, essentially, the whole thing is random. Secondly, when you want to convert your crystals into accessories for your avatar, random selection determines which accessory you receive, even though, again, there is a semblance of agency. Different accessories have different power values. This extended use of what the developers call ‘the thrill of uncertain rewards’ is certainly interesting, but how effective it is is another matter. My own reaction, after quite some time spent ‘studying’, to getting no crystals or an avatar accessory that I didn’t want was primarily frustration, rather than motivation to carry on. I have no idea how typical my reaction (more ‘treadmill’ than ‘thrill’) might be.

Unsurprisingly, for an app that has so obviously thought carefully about gamification, players are encouraged to interact with each other. As part of the early promotion, WAM is running, from 15 November to 19 December, a free ‘team challenge tournament’, allowing teams of up to 8 players to compete against each other. Ingeniously, it would appear to allow teams and players of varying levels of English to play together, with the app’s algorithms determining each individual’s level of lexical knowledge and therefore the items that will be presented / tested. Social interaction is known to be an important component of successful games (Dehghanzadeh et al., 2019), but for vocabulary apps there’s a huge challenge. In order to learn vocabulary from an app, learners need to put in time – on a regular basis. Team challenge tournaments may help with initial on-boarding of players, but, in the end, learning from a vocabulary app is inevitably and largely a solitary pursuit. Over time, social interaction is unlikely to be maintained, and it is, in any case, of a very limited nature. The other features of successful games – playful freedom and intrinsically motivating tasks (Driver, 2012) – are also absent from vocabulary apps. Playful freedom is mostly incompatible with points, badges and leaderboards. And flashcard tasks, however intrinsically motivating they may be at the outset, will always become repetitive after a while. In the end, what’s left, for those users who hang around long enough, is the reward system.

It’s also worth noting that this free challenge is of limited duration: it is a marketing device attempting to push you towards the non-free use of the app, once the initial promotion is over.

Gamified motivation tools are only of value, of course, if they motivate learners to spend their time doing things that are of clear learning value. To evaluate the learning potential of WAM, then, we need to look at the content (the ‘learning objects’) and the learning tasks that supposedly lead to acquisition of these items.

When you first use WAM, you need to play for about 20 minutes, at which point algorithms determine ‘how many words [you] know and [you can] see scores for English tests such as; TOEFL, TOEIC, IELTS, EIKEN, Kyotsu Shiken, CEFR, SAT and GRE’. The developers claim that these scores correlate pretty highly with actual test scores: ‘they are about as accurate as the tests themselves’, they say. If Browne and Culligan had been behind the app, I would have been tempted to accept the claim – with reservations: after all, it still allows for one item out of 5 to be wrongly identified. But, what is this CEFR test score that is referred to? There is no CEFR test, although many tests are correlated with CEFR. The two tools that I am most familiar with which allocate CEFR levels to individual words – Cambridge’s English Vocabulary Profile and Pearson’s Global Scale of English – often conflict in their results. I suspect that ‘CEFR’ was just thrown into the list of tests as an attempt to broaden the app’s appeal.

English target words are presented and practised with their translation ‘equivalents’ in Japanese. For the moment, Japanese is the only language available, which means the app is of little use to learners who don’t know any Japanese. It’s now well-known that bilingual pairings are more effective in deliberate language learning than using definitions in the same language as the target items. This becomes immediately apparent when, for example, a word like ‘something’ is defined (by WAM) as ‘a thing not known or specified’ and ‘anything’ as ‘a thing of whatever kind’. But although I’m in no position to judge the Japanese translations, there are reasons why I would want to check the spreadsheet before recommending the app. ‘Lady’ is defined as ‘polite word for a woman’; ‘missus’ is defined as ‘wife’; and ‘aye’ is defined as ‘yes’. All of these definitions are, at best, problematic; at worst, they are misleading. Are the Japanese translations more helpful? I wonder … Perhaps these are simply words that do not lend themselves to flashcard treatment?

Because I tested in to the app at C1 level, I was not able to evaluate the selection of words at lower levels. A pity. Instead, I was presented with words like ‘ablution’, ‘abrade’, ‘anode’, and ‘auspice’. The app claims to be suitable ‘for both second-language learners and native speakers’. For lower levels of the former, this may be true (but without looking at the lexical spreadsheets, I can’t tell). But for higher levels, however much fun this may be for some people, it seems unlikely that you’ll learn very much of any value. Outside of words in, say, the top 8000 frequency band, it is practically impossible to differentiate the ‘surrender value’ of words in any meaningful way. Deliberate learning of vocabulary only makes sense with high frequency words that you have a chance of encountering elsewhere. You’d be better off reading, extensively, rather than learning random words from an app. Words, which (for reasons I’ll come on to) you probably won’t actually learn anyway.

With very few exceptions, the learning objects in WAM are single words, rather than phrases, even when the item is of little or no value outside its use in a phrase. ‘Betide’ is defined as ‘to happen to; befall’ but this doesn’t tell a learner much that is useful. It’s practically only ever used following ‘woe’ (but what does ‘woe’ mean?!). Learning items can be checked in the ‘study guide’, which will show that ‘betide’ typically follows ‘woe’, but unless you choose to refer to the study guide (and there’s no reason, in a case like this, that you would know that you need to check things out more fully), you’ll be none the wiser. In other words, checking the study guide is unlikely to betide you. ‘Wee’, as another example, is treated as two items: (1) meaning ‘very small’ as in ‘wee baby’, and (2) meaning ‘very early in the morning’ as in ‘in the wee hours’. For the latter, ‘wee’ can only collocate with ‘in the’ and ‘hours’, so it makes little sense to present it as a single word. This is also an example of how, in some cases, different meanings of particular words are treated as separate learning objects, even when the two meanings are very close and, in my view, are hardly worth learning separately. Examples include ‘czar’ and ‘assonance’. Sometimes, cognates are treated as separate learning objects (e.g. ‘adulterate’ and ‘adulteration’ or ‘dolor’ and ‘dolorous’); with other words (e.g. ‘effulgence’), only one grammatical form appears to be given. I could not begin to figure out any rationale behind any of this.

All in all, then, there are reasons to be a little skeptical about some of the content. Up to level B2 – which, in my view, is the highest level at which it makes sense to use vocabulary flashcards – it may be of value, so long as your first language is Japanese. But given the claim that it can help you prepare for the ‘CEFR test’, I have to wonder …

The learning tasks require players to match target items to translations / definitions (in both directions), with the target item sometimes in written form, sometimes spoken. Users do not, as far as I can tell, ever have to produce the target item: they only have to select. The learning relies on spaced repetition, but there is no generative effect (known to enhance memorisation). When I was experimenting, there were a few words that I did not know, but I was usually able to get the correct answer by eliminating the distractors (a choice of one from three gives players a reasonable chance of guessing correctly). WAM does not teach users how to produce words; its focus is on receptive knowledge (of a limited kind). I learn, for example, what a word like ‘aye’ or ‘missus’ kind of means, but I learn nothing about how to use it appropriately. Contrary to the claims in WAM’s bumf (that ‘all senses and dimensions of each word are fully acquired’), reading and listening comprehension speeds may be improved, but appropriate and accurate use of these words in speaking and writing is much less likely to follow. Does WAM really ‘strengthen and expand the foundation levels of cognition that support all higher level thinking’, as is claimed?

Perhaps it’s unfair to mention some of the more dubious claims of WAM’s promotional material, but here is a small selection, anyway: ‘WAM unleashes the full potential of natural motivation’. ‘WAM promotes Flow by carefully managing the ratio of unknown words. Your mind moves freely in the channel below frustration and above boredom’.

WAM is certainly an interesting project, but, like all the vocabulary apps I have ever looked at, there have to be trade-offs between optimal task design and what will fit on a mobile screen, between freedoms and flexibility for the user and the requirements of gamified points systems, between the amount of linguistic information that is desirable and the amount that spaced repetition can deal with, between attempting to make the app suitable for the greatest number of potential users and making it especially appropriate for particular kinds of users. Design considerations are always a mix of the pedagogical and the practical / commercial. And, of course, the financial. And, like most edtech products, the claims for its efficacy need to be treated with a bucket of salt.

References

Dehghanzadeh, H., Fardanesh, H., Hatami, J., Talaee, E. & Noroozi, O. (2019) Using gamification to support learning English as a second language: a systematic review, Computer Assisted Language Learning, DOI: 10.1080/09588221.2019.1648298

Driver, P. (2012) The Irony of Gamification. In English Digital Magazine 3, British Council Portugal, pp. 21 – 24 http://digitaldebris.info/digital-debris/2011/12/31/the-irony-of-gamification-written-for-ied-magazine.html

Howard-Jones, P. & Jay, T. (2016) Reward, learning and games. Current Opinion in Behavioral Sciences, 10: 65 – 72

What has neuroscience ever done for us (in ELT)?

Five years ago, in 2016, there was an interesting debate in the pages of the journal ‘Psychological Review’. It began with an article by Jeffrey Bowers (2016a), a psychologist at the University of Bristol, who argued that neuroscience (as opposed to psychology) has little, or nothing, to offer us, and is unlikely ever to be able to do so, in terms of improving classroom instruction. He wasn’t the first to question the relevance of neuroscience to education (see, for example, Willingham, 2009), but this was a full-frontal attack. Bowers argued that ‘neuroscience rarely offers insights into instruction above and beyond psychology’ and that neuroscientific evidence that the brain changes in response to instruction are irrelevant. His article was followed by two counter-arguments (Gabrieli, 2016; Howard-Jones, et al., 2016), which took him to task for too narrowly limiting the scope of education to classroom instruction (neglecting, for example, educational policy), for ignoring the predictive power of neuroimaging on neurodevelopmental differences (and, therefore, its potential value in individualising curricula), and for failing to take account of the progress that neuroscience, in collaboration with educators, has already made. Bowers’ main argument, that educational neuroscience had little to tell us about teaching, was not really addressed in the counter-arguments, and Bowers (2016b) came back with a counter-counter-rebuttal.

The brain responding to seductive details

In some ways, the debate, like so many of the kind, suffered from the different priorities of the participants. For Gabriele and Howard-Jones et al., Bowers had certainly overstated his case, but they weren’t entirely in disagreement with him. Paul Howard-Jones has been quoted by André Hedlund as saying that ‘all neuroscience can do is confirm what we’ve been doing all along and give us new insights into a couple of new things’. One of Howard-Jones’ co-authors, Usha Goswami, director of the Centre for Neuroscience in Education at the University of Cambridge, has said that ‘there is a gulf between current science and classroom applications’ (Goswami, 2006).

For teachers, though, it is the classroom applications that are of interest. Claims for the relevance of neuroscience to ELT have been made by many. We [in ESL / EFL] need it, writes Curtis Kelly (2017). Insights from neuroscience can, apparently, make textbooks more ‘brain friendly’ (Helgesen & Kelly, 2015). Herbert Puchta’s books are advertised by Cambridge University Press as ‘based on the latest insights into how the brain works fresh from the field of neuroscience’. You can watch a British Council talk by Rachael Roberts, entitled ‘Using your brain: what neuroscience can teach us about learning’. And, in the year following the Bowers debate, Carol Lethaby and Patricia Harries gave a presentation at IATEFL Glasgow (Lethaby & Harries, 2018) entitled ‘Research and teaching: What has neuroscience ever done for us?’ – a title that I have lifted for this blog post. Lethaby and Harries provide a useful short summary of the relevance of neuroscience to ELT, and I will begin my discussion with that. They expand on this in their recent book (Lethaby, Mayne & Harries, 2021), a book I highly recommend.

So what, precisely, does neuroscience have to tell English language teachers? Lethaby and Harries put forward three main arguments. Firstly, neuroscience can help us to bust neuromyths (the examples they give are right / left brain dominance and learning styles). Secondly, it can provide information that informs teaching (the examples given are the importance of prior knowledge and the value of translation). Finally, it can validate existing best practice (the example given is the importance of prior knowledge). Let’s take a closer look.

I have always enjoyed a bit of neuromyth busting and I wrote about ‘Left brains and right brains in English language teaching’ a long time ago. It is certainly true that neuroscience has helped to dispel this myth: it is ‘simplistic at best and utter hogwash at worst’ (Dörnyei, 2009: 49). However, we did not need neuroscience to rubbish the practical teaching applications of this myth, which found their most common expression in Neuro-Linguistic Programming (NLP) and Brain Gym. Neuroscience simply banged in the final nail in the coffin of these trends. The same is true for learning styles and the meshing hypothesis. It’s also worth noting that, despite the neuroscientific evidence, such myths are taking a long time to die … a point I will return to at the end of this post.

Lethaby and Harries’s second and third arguments are essentially the same, unless, in their second point they are arguing that neuroscience can provide new information. I struggle, however, to see anything that is new. Neuroimaging apparently shows that the medial prefrontal cortex is activated when prior knowledge is accessed, but we have long known (since Vygotsky, at least!) that effective learning builds on previous knowledge. Similarly, the amygdala (known to be associated with the processing of emotions) may play an important role in learning, but we don’t need to know about the amygdala to understand the role of affect in learning. Lastly, the neuroscientific finding that different languages are not ‘stored’ in separate parts of the brain (Spivey & Hirsch, 2003) is useful to substantiate arguments that translation can have a positive role to play in learning another language, but convincing arguments predate findings such as these by many, many years. This would all seem to back up Howard-Jones’s observation about confirming what we’ve been doing and giving us new insights into a couple of new things. It isn’t the most compelling case for the relevance of neuroscience to ELT.

Chapter 2 of Carol Lethaby’s new book, ‘An Introduction to Evidence-based Teaching in the English Language Classroom’ is devoted to ‘Science and neuroscience’. The next chapter is called ‘Psychology and cognitive science’ and practically all the evidence for language teaching approaches in the rest of the book is drawn from cognitive (rather than neuro-) science. I think the same is true for the work of Kelly, Helgesen, Roberts and Puchta that I mentioned earlier.

It is perhaps the case these days that educationalists prefer to refer to ‘Mind, Brain, and Education Science’ (MBE) – the ‘intersection of neuroscience, education, and psychology’ – rather than educational neuroscience, but, looking at the literature of MBE, there’s a lot more education and psychology than there is neuroscience (although the latter always gets a mention). Probably the most comprehensive and well-known volume of practical ideas deriving from MBE is ‘Making Classrooms Better’ (Tokuhama-Espinosa, 2014). Of the 50 practical applications listed, most are either inspired by the work of John Hattie (2009) or the work of cognitive psychologists. Neuroscience hardly gets a look in.

To wrap up, I’d like to return to the question of neuroscience’s role in busting neuromyths. References to neuroscience, especially when accompanied by fMRI images, have a seductive appeal to many: they confer a sense of ‘scientific’ authority. Many teachers, it seems, are keen to hear about neuroscience (Pickering & Howard-Jones, 2007). Even when the discourse contains irrelevant neuroscientific information (diagrams of myelination come to mind), it seems that many of us find this satisfying (Weisberg et al., 2015; Weisberg et al., 2008). It gives an illusion of explanatory depth (Rozenblit & Keil, 2002), the so-called ‘seductive details effect’. You are far more likely to see conference presentations, blog posts and magazine articles extolling the virtues of neuroscientific findings than you are to come across things like I am writing here. But is it possible that the much-touted idea that neuroscience can bust neuromyths is itself a myth?

Sadly, we have learnt in recent times that scientific explanations have only very limited impact on the beliefs of large swathes of the population (including teachers, of course). Think of climate change and COVID. Why should neuroscience be any different? It probably isn’t. Scurich & Shniderman (2014) found that ‘neuroscience is more likely to be accepted and credited when it confirms prior beliefs’. We are more likely to accept neuroscientific findings because we ‘find them intuitively satisfying, not because they are accurate’ (Weisberg, et al. 2008). Teaching teachers about educational neuroscience may not make much, if any, difference (Tham et al., 2019). I think there is a danger in using educational neuroscience, seductive details and all, to validate what we already do (as opposed to questioning what we do). And for those who don’t already do these things, they’ll probably ignore such findings as there are, anyway.

References

Bowers, J. (2016a) The practical and principled problems with educational Neuroscience. Psychological Review 123 (5) 600 – 612

Bowers, J.S. (2016b) Psychology, not educational neuroscience, is the way forward for improving educational outcomes for all children: Reply to Gabrieli (2016) and Howard-Jones et al. (2016). Psychological Review. 123 (5):628-35.

Dörnyei, Z. (2009) The Psychology of Second Language Acquisition. Oxford: Oxford University Press

Gabrieli, J.D. (2016) The promise of educational neuroscience: Comment on Bowers (2016). Psychological Review. 123 (5):613-9

Goswami , U. (2006). Neuroscience and education: From research to practice? Nature Reviews Neuroscience, 7: 406 – 413

Hattie, J. (2009) Visible Learning: A synthesis of over 800 meta-analyses relating to achievement. London: Routledge

Helgesen, M. & Kelly, C. (2015) Do-it-yourself: Ways to make your textbook more brain-friendly’ SPELT Quarterly, 30 (3): 32 – 37

Howard-Jones, P.A., Varma. S., Ansari, D., Butterworth, B., De Smedt, B., Goswami, U., Laurillard, D. & Thomas, M. S. (2016) The principles and practices of educational neuroscience: Comment on Bowers (2016). Psychological Review. 123 (5):620-7

Kelly, C. (2017) The Brain Studies Boom: Using Neuroscience in ESL/EFL Teacher Training. In Gregersen, T. S. & MacIntyre, P. D. (Eds.) Innovative Practices in Language Teacher Education pp.79-99 Springer

Lethaby, C. & Harries, P. (2018) Research and teaching: What has neuroscience ever done for us?’ in Pattison, T. (Ed.) IATEFL Glasgow Conference Selections 2017. Faversham, Kent, UK: IATEFL  p. 36- 37

Lethaby, C., Mayne, R. & Harries, P. (2021) An Introduction to Evidence-Based Teaching in the English Language Classroom. Shoreham-by-Sea: Pavilion Publishing

McCabe, D.P. & Castel, A.D. (2008) Seeing is believing: The effect of brain images on judgments of scientific reasoning. Cognition 107: 343–352.

Pickering, S. J. & Howard-Jones, P. (2007) Educators’ views on the role of neuroscience in education: findings from a study of UK and international perspectives. Mind Brain Education 1: 109–113.

Rozenblit, L., & Keil, F. (2002). The misunderstood limits of folk science: an illusion of explanatory depth. Cognitive science, 26(5), 521–562.

Scurich, N., & Shniderman, A. (2014) The selective allure of neuroscientific explanations. PLOS One, 9 (9), e107529. http://dx.doi.org/10.1371/journal.pone. 0107529.

Spivey, M. V. & Hirsch, J. (2003) ‘Shared and separate systems in bilingual language processing: Converging evidence from eyetracking and brain imaging’ Brain and Language, 86: 70 – 82

Tham, R., Walker, Z., Tan, S.H.D., Low, L.T. & Annabel Chan, S.H. (2019) Translating educational neuroscience for teachers. Learning: Research and Practice, 5 (2): 149-173 Singapore: National Institute of Education

Tokuhama-Espinosa, T. (2014) Making Classrooms Better. New York: Norton

Weisberg, D. S., Taylor, J. C. V. & Hopkins, E.J. (2015) Deconstructing the seductive allure of neuroscience explanations. Judgment and Decision Making, Vol. 10, No. 5, September 2015, pp. 429–441

Weisberg, D. S., Keil, F. C., Goodstein, J., Rawson, E., & Gray, J. R. (2008). The seductive allure of neuroscience explanations. Journal of cognitive neuroscience, 20 (3): 470–477.

Willingham, D. T. (2009). Three problems in the marriage of neuroscience and education. Cortex, 45: 54-55.