Posts Tagged ‘chatbots’

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

In May of last year, EL Gazette had a story entitled ‘Your new English language teacher is a robot’ that was accompanied by a stock photo of a humanoid robot, Pepper (built by SoftBank Robotics). The story was pure clickbait and the picture had nothing to do with it. The article actually concerned a chatbot (EAP Talk) to practise EAP currently under development at a Chinese university. There’s nothing especially new about chatbots: I last blogged about them in 2016 and interest in them, both research and practical, dates back to the 1970s (Lee et al., 2020). There’s nothing, as far as I can see, especially new about the Chinese EAP chatbot project either. The article concludes by saying that the academic behind the project ‘does not believe that AI can ever replace a human teacher’, but that chatbots might offer some useful benefits.

The benefits are, however, limited – a point that is acknowledged even by chatbot enthusiasts like Lee et al (2020). We are some way from having chatbots that we can actually have meaningful conversations with, but they do appear to have some potential as ‘intelligent tutoring systems’ to provide practice of and feedback on pre-designated bits of language (especially vocabulary and phrases). The main benefit that is usually given, as in the EL Gazette article, is that they are non-judgemental and may, therefore, be appropriate for shy or insecure learners.

Social robots, of the kind used in the illustration for the EL Gazette story, are, of course, not the same as chatbots. Chatbots, like EAP Talk, can be incorporated into all sorts of devices (notably phones, tablets and laptops) and all sorts of applications. If social robots are to be used for language learning, they will clearly need to incorporate chatbots, but in what ways could the other features of robots facilitate language acquisition? Pepper (the robot in the picture) has ‘touch sensors, LEDs and microphones for multimodal interactions’, along with ‘infrared sensors, bumpers, an inertial unit, 2D and 3D cameras, and sonars for omnidirectional and autonomous navigation’. How could these features help language acquisition?

Lee and Lee (2022) attempt to provide an answer to this question. Here’s what they have come up with:

By virtue of their physical embodiment, social robots have been suggested to provide language learners with direct and physical interactions, which is considered one of the basic ingredients for language learning. In addition, as social robots are generally humanoids or anthropomorphized animal shapes, they have been valued for their ability to serve as familiar conversational partners, having potential to lower the affective filter of language learners.

Is there any research evidence to back up these claims? The short answer is no. Motivation and engagement may sometimes be positively impacted, but we can’t say any more than that. As far as learning is concerned, Lee and Lee (2022: 121) write: involving social robots led to statistically similar or even higher [English language learning] outcomes compared with traditional ELT contexts (i.e. no social robot). In other words, social robots did not, on the whole, have a negative impact on learning outcomes. Hardly grounds for wild enthusiasm … Still, Lee and Lee, in the next line, refer to the ‘positive effectiveness of social robots in English teaching’ before proceeding to enumerate the ways in which these robots could be used in English language learning. Doesn’t ELT Journal have editors to pick up on this kind of thing?

So, how could these robots be used? Lee and Lee suggest (for younger learners) one-on-one vocabulary tutoring, dialogue practice, more vocabulary teaching, and personalized feedback. That’s it. It’s worth noting that all of these functions could equally well be carried out by chatbots as by social robots.

Lee and Lee discuss and describe the social robot, NAO6, also built by SoftBank Robotics. It’s a smaller and cheaper cousin of the Pepper robot that illustrates the EL Gazette article. Among Lee and Lee’s reasons for using social robots is that they ‘have become more accessible due to ever-lower costs’: NAO6 costs around £350 a month to rent. Buying it outright is also an option. Eduporium (‘Empowering the future with technology’) has one on offer for $12,990.00. According to the blurb, it helps ‘teach coding, brings literature to life, enhances special education, and allows for training simulations. Plus, its educational solutions include an intuitive interface, remote learning, and various applications for accessibility!’

It’s easy enough to understand why EL Gazette uses clickbait from time to time. I’m less clear about why ELT Journal would print this kind of nonsense. According to Lee and Lee, further research into social robots ‘would initiate a new era of language learning’ in which the robots will become ‘an important addition to the ELT arsenal’. Yeah, right …

References

Lee, H. & Lee, J. H. (2022) Social robots for English language teaching. ELT Journal 76 (1): 119 – 124

Lee, J. H., Yang, H., Shin D. & Kim, H. (2020) Chatbots. ELT Journal 74 (3): 338 – 3444

Colloquium

At the beginning of March, I’ll be going to Cambridge to take part in a Digital Learning Colloquium (for more information about the event, see here ). One of the questions that will be explored is how research might contribute to the development of digital language learning. In this, the first of two posts on the subject, I’ll be taking a broad overview of the current state of play in edtech research.

I try my best to keep up to date with research. Of the main journals, there are Language Learning and Technology, which is open access; CALICO, which offers quite a lot of open access material; and reCALL, which is the most restricted in terms of access of the three. But there is something deeply frustrating about most of this research, and this is what I want to explore in these posts. More often than not, research articles end with a call for more research. And more often than not, I find myself saying ‘Please, no, not more research like this!’

First, though, I would like to turn to a more reader-friendly source of research findings. Systematic reviews are, basically literature reviews which can save people like me from having to plough through endless papers on similar subjects, all of which contain the same (or similar) literature review in the opening sections. If only there were more of them. Others agree with me: the conclusion of one systematic review of learning and teaching with technology in higher education (Lillejord et al., 2018) was that more systematic reviews were needed.

Last year saw the publication of a systematic review of research on artificial intelligence applications in higher education (Zawacki-Richter, et al., 2019) which caught my eye. The first thing that struck me about this review was that ‘out of 2656 initially identified publications for the period between 2007 and 2018, 146 articles were included for final synthesis’. In other words, only just over 5% of the research was considered worthy of inclusion.

The review did not paint a very pretty picture of the current state of AIEd research. As the second part of the title of this review (‘Where are the educators?’) makes clear, the research, taken as a whole, showed a ‘weak connection to theoretical pedagogical perspectives’. This is not entirely surprising. As Bates (2019) has noted: ‘since AI tends to be developed by computer scientists, they tend to use models of learning based on how computers or computer networks work (since of course it will be a computer that has to operate the AI). As a result, such AI applications tend to adopt a very behaviourist model of learning: present / test / feedback.’ More generally, it is clear that technology adoption (and research) is being driven by technology enthusiasts, with insufficient expertise in education. The danger is that edtech developers ‘will simply ‘discover’ new ways to teach poorly and perpetuate erroneous ideas about teaching and learning’ (Lynch, 2017).

This, then, is the first of my checklist of things that, collectively, researchers need to do to improve the value of their work. The rest of this list is drawn from observations mostly, but not exclusively, from the authors of systematic reviews, and mostly come from reviews of general edtech research. In the next blog post, I’ll look more closely at a recent collection of ELT edtech research (Mavridi & Saumell, 2020) to see how it measures up.

1 Make sure your research is adequately informed by educational research outside the field of edtech

Unproblematised behaviourist assumptions about the nature of learning are all too frequent. References to learning styles are still fairly common. The most frequently investigated skill that is considered in the context of edtech is critical thinking (Sosa Neira, et al., 2017), but this is rarely defined and almost never problematized, despite a broad literature that questions the construct.

2 Adopt a sceptical attitude from the outset

Know your history. Decades of technological innovation in education have shown precious little in the way of educational gains and, more than anything else, have taught us that we need to be sceptical from the outset. ‘Enthusiasm and praise that are directed towards ‘virtual education, ‘school 2.0’, ‘e-learning and the like’ (Selwyn, 2014: vii) are indications that the lessons of the past have not been sufficiently absorbed (Levy, 2016: 102). The phrase ‘exciting potential’, for example, should be banned from all edtech research. See, for example, a ‘state-of-the-art analysis of chatbots in education’ (Winkler & Söllner, 2018), which has nothing to conclude but ‘exciting potential’. Potential is fine (indeed, it is perhaps the only thing that research can unambiguously demonstrate – see section 3 below), but can we try to be a little more grown-up about things?

3 Know what you are measuring

Measuring learning outcomes is tricky, to say the least, but it’s understandable that researchers should try to focus on them. Unfortunately, ‘the vast array of literature involving learning technology evaluation makes it challenging to acquire an accurate sense of the different aspects of learning that are evaluated, and the possible approaches that can be used to evaluate them’ (Lai & Bower, 2019). Metrics such as student grades are hard to interpret, not least because of the large number of variables and the danger of many things being conflated in one score. Equally, or possibly even more, problematic, are self-reporting measures which are rarely robust. It seems that surveys are the most widely used instrument in qualitative research (Sosa Neira, et al., 2017), but these will tell us little or nothing when used for short-term interventions (see point 5 below).

4 Ensure that the sample size is big enough to mean something

In most of the research into digital technology in education that was analysed in a literature review carried out for the Scottish government (ICF Consulting Services Ltd, 2015), there were only ‘small numbers of learners or teachers or schools’.

5 Privilege longitudinal studies over short-term projects

The Scottish government literature review (ICF Consulting Services Ltd, 2015), also noted that ‘most studies that attempt to measure any outcomes focus on short and medium term outcomes’. The fact that the use of a particular technology has some sort of impact over the short or medium term tells us very little of value. Unless there is very good reason to suspect the contrary, we should assume that it is a novelty effect that has been captured (Levy, 2016: 102).

6 Don’t forget the content

The starting point of much edtech research is the technology, but most edtech, whether it’s a flashcard app or a full-blown Moodle course, has content. Research reports rarely give details of this content, assuming perhaps that it’s just fine, and all that’s needed is a little tech to ‘present learners with the ‘right’ content at the ‘right’ time’ (Lynch, 2017). It’s a foolish assumption. Take a random educational app from the Play Store, a random MOOC or whatever, and the chances are you’ll find it’s crap.

7 Avoid anecdotal accounts of technology use in quasi-experiments as the basis of a ‘research article’

Control (i.e technology-free) groups may not always be possible but without them, we’re unlikely to learn much from a single study. What would, however, be extremely useful would be a large, collated collection of such action-research projects, using the same or similar technology, in a variety of settings. There is a marked absence of this kind of work.

8 Enough already of higher education contexts

Researchers typically work in universities where they have captive students who they can carry out research on. But we have a problem here. The systematic review of Lundin et al (2018), for example, found that ‘studies on flipped classrooms are dominated by studies in the higher education sector’ (besides lacking anchors in learning theory or instructional design). With some urgency, primary and secondary contexts need to be investigated in more detail, not just regarding flipped learning.

9 Be critical

Very little edtech research considers the downsides of edtech adoption. Online safety, privacy and data security are hardly peripheral issues, especially with younger learners. Ignoring them won’t make them go away.

More research?

So do we need more research? For me, two things stand out. We might benefit more from, firstly, a different kind of research, and, secondly, more syntheses of the work that has already been done. Although I will probably continue to dip into the pot-pourri of articles published in the main CALL journals, I’m looking forward to a change at the CALICO journal. From September of this year, one issue a year will be thematic, with a lead article written by established researchers which will ‘first discuss in broad terms what has been accomplished in the relevant subfield of CALL. It should then outline which questions have been answered to our satisfaction and what evidence there is to support these conclusions. Finally, this article should pose a “soft” research agenda that can guide researchers interested in pursuing empirical work in this area’. This will be followed by two or three empirical pieces that ‘specifically reflect the research agenda, methodologies, and other suggestions laid out in the lead article’.

But I think I’ll still have a soft spot for some of the other journals that are coyer about their impact factor and that can be freely accessed. How else would I discover (it would be too mean to give the references here) that ‘the effective use of new technologies improves learners’ language learning skills’? Presumably, the ineffective use of new technologies has the opposite effect? Or that ‘the application of modern technology represents a significant advance in contemporary English language teaching methods’?

References

Bates, A. W. (2019). Teaching in a Digital Age Second Edition. Vancouver, B.C.: Tony Bates Associates Ltd. Retrieved from https://pressbooks.bccampus.ca/teachinginadigitalagev2/

ICF Consulting Services Ltd (2015). Literature Review on the Impact of Digital Technology on Learning and Teaching. Edinburgh: The Scottish Government. https://dera.ioe.ac.uk/24843/1/00489224.pdf

Lai, J.W.M. & Bower, M. (2019). How is the use of technology in education evaluated? A systematic review. Computers & Education, 133(1), 27-42. Elsevier Ltd. Retrieved January 14, 2020 from https://www.learntechlib.org/p/207137/

Levy, M. 2016. Researching in language learning and technology. In Farr, F. & Murray, L. (Eds.) The Routledge Handbook of Language Learning and Technology. Abingdon, Oxon.: Routledge. pp.101 – 114

Lillejord S., Børte K., Nesje K. & Ruud E. (2018). Learning and teaching with technology in higher education – a systematic review. Oslo: Knowledge Centre for Education https://www.forskningsradet.no/siteassets/publikasjoner/1254035532334.pdf

Lundin, M., Bergviken Rensfeldt, A., Hillman, T. et al. (2018). Higher education dominance and siloed knowledge: a systematic review of flipped classroom research. International Journal of Educational Technology in Higher Education 15, 20 (2018) doi:10.1186/s41239-018-0101-6

Lynch, J. (2017). How AI Will Destroy Education. Medium, November 13, 2017. https://buzzrobot.com/how-ai-will-destroy-education-20053b7b88a6

Mavridi, S. & Saumell, V. (Eds.) (2020). Digital Innovations and Research in Language Learning. Faversham, Kent: IATEFL

Selwyn, N. (2014). Distrusting Educational Technology. New York: Routledge

Sosa Neira, E. A., Salinas, J. and de Benito Crosetti, B. (2017). Emerging Technologies (ETs) in Education: A Systematic Review of the Literature Published between 2006 and 2016. International Journal of Emerging Technologies in Education, 12 (5). https://online-journals.org/index.php/i-jet/article/view/6939

Winkler, R. & Söllner, M. (2018): Unleashing the Potential of Chatbots in Education: A State-Of-The-Art Analysis. In: Academy of Management Annual Meeting (AOM). Chicago, USA. https://www.alexandria.unisg.ch/254848/1/JML_699.pdf

Zawacki-Richter, O., Bond, M., Marin, V. I. And Gouverneur, F. (2019). Systematic review of research on artificial intelligence applications in higher education – where are the educators? International Journal of Educational Technology in Higher Education 2019

ltsigIt’s hype time again. Spurred on, no doubt, by the current spate of books and articles  about AIED (artificial intelligence in education), the IATEFL Learning Technologies SIG is organising an online event on the topic in November of this year. Currently, the most visible online references to AI in language learning are related to Glossika , basically a language learning system that uses spaced repetition, whose marketing department has realised that references to AI might help sell the product. GlossikaThey’re not alone – see, for example, Knowble which I reviewed earlier this year .

In the wider world of education, where AI has made greater inroads than in language teaching, every day brings more stuff: How artificial intelligence is changing teaching , 32 Ways AI is Improving Education , How artificial intelligence could help teachers do a better job , etc., etc. There’s a full-length book by Anthony Seldon, The Fourth Education Revolution: will artificial intelligence liberate or infantilise humanity? (2018, University of Buckingham Press) – one of the most poorly researched and badly edited books on education I’ve ever read, although that won’t stop it selling – and, no surprises here, there’s a Pearson commissioned report called Intelligence Unleashed: An argument for AI in Education (2016) which is available free.

Common to all these publications is the claim that AI will radically change education. When it comes to language teaching, a similar claim has been made by Donald Clark (described by Anthony Seldon as an education guru but perhaps best-known to many in ELT for his demolition of Sugata Mitra). In 2017, Clark wrote a blog post for Cambridge English (now unavailable) entitled How AI will reboot language learning, and a more recent version of this post, called AI has and will change language learning forever (sic) is available on Clark’s own blog. Given the history of the failure of education predictions, Clark is making bold claims. Thomas Edison (1922) believed that movies would revolutionize education. Radios were similarly hyped in the 1940s and in the 1960s it was the turn of TV. In the 1980s, Seymour Papert predicted the end of schools – ‘the computer will blow up the school’, he wrote. Twenty years later, we had the interactive possibilities of Web 2.0. As each technology failed to deliver on the hype, a new generation of enthusiasts found something else to make predictions about.

But is Donald Clark onto something? Developments in AI and computational linguistics have recently resulted in enormous progress in machine translation. Impressive advances in automatic speech recognition and generation, coupled with the power that can be packed into a handheld device, mean that we can expect some re-evaluation of the value of learning another language. Stephen Heppell, a specialist at Bournemouth University in the use of ICT in Education, has said: ‘Simultaneous translation is coming, making language teachers redundant. Modern languages teaching in future may be more about navigating cultural differences’ (quoted by Seldon, p.263). Well, maybe, but this is not Clark’s main interest.

Less a matter of opinion and much closer to the present day is the issue of assessment. AI is becoming ubiquitous in language testing. Cambridge, Pearson, TELC, Babbel and Duolingo are all using or exploring AI in their testing software, and we can expect to see this increase. Current, paper-based systems of testing subject knowledge are, according to Rosemary Luckin and Kristen Weatherby, outdated, ineffective, time-consuming, the cause of great anxiety and can easily be automated (Luckin, R. & Weatherby, K. 2018. ‘Learning analytics, artificial intelligence and the process of assessment’ in Luckin, R. (ed.) Enhancing Learning and Teaching with Technology, 2018. UCL Institute of Education Press, p.253). By capturing data of various kinds throughout a language learner’s course of study and by using AI to analyse learning development, continuous formative assessment becomes possible in ways that were previously unimaginable. ‘Assessment for Learning (AfL)’ or ‘Learning Oriented Assessment (LOA)’ are two terms used by Cambridge English to refer to the potential that AI offers which is described by Luckin (who is also one of the authors of the Pearson paper mentioned earlier). In practical terms, albeit in a still very limited way, this can be seen in the CUP course ‘Empower’, which combines CUP course content with validated LOA from Cambridge Assessment English.

Will this reboot or revolutionise language teaching? Probably not and here’s why. AIED systems need to operate with what is called 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. Some subjects (especially STEM subjects) ‘lend themselves much more readily to having their domains represented in ways that can be automatically reasoned about’ (du Boulay, D. et al., 2018. ‘Artificial intelligences and big data technologies to close the achievement gap’ in Luckin, R. (ed.) Enhancing Learning and Teaching with Technology, 2018. UCL Institute of Education Press, p.258). This is why most AIED systems have been built to teach these areas. Language are rather different. We simply do not have a domain knowledge model, except perhaps for the very lowest levels of language learning (and even that is highly questionable). Language learning is probably not, or not primarily, about acquiring subject knowledge. Debate still rages about the relationship between explicit language knowledge and language competence. AI-driven formative assessment will likely focus most on explicit language knowledge, as does most current language teaching. This will not reboot or revolutionise anything. It will more likely reinforce what is already happening: a model of language learning that assumes there is a strong interface between explicit knowledge and language competence. It is not a model that is shared by most SLA researchers.

So, one thing that AI can do (and is doing) for language learning is to improve the algorithms that determine the way that grammar and vocabulary are presented to individual learners in online programs. AI-optimised delivery of ‘English Grammar in Use’ may lead to some learning gains, but they are unlikely to be significant. It is not, in any case, what language learners need.

AI, Donald Clark suggests, can offer personalised learning. Precisely what kind of personalised learning this might be, and whether or not this is a good thing, remains unclear. A 2015 report funded by the Gates Foundation found that we currently lack evidence about the effectiveness of personalised learning. We do not know which aspects of personalised learning (learner autonomy, individualised learning pathways and instructional approaches, etc.) or which combinations of these will lead to gains in language learning. The complexity of the issues means that we may never have a satisfactory explanation. You can read my own exploration of the problems of personalised learning starting here .

What’s left? Clark suggests that chatbots are one area with ‘huge potential’. I beg to differ and I explained my reasons eighteen months ago . Chatbots work fine in very specific domains. As Clark says, they can be used for ‘controlled practice’, but ‘controlled practice’ means practice of specific language knowledge, the practice of limited conversational routines, for example. It could certainly be useful, but more than that? Taking things a stage further, Clark then suggests more holistic speaking and listening practice with Amazon Echo, Alexa or Google Home. If and when the day comes that we have general, as opposed to domain-specific, AI, chatting with one of these tools would open up vast new possibilities. Unfortunately, general AI does not exist, and until then Alexa and co will remain a poor substitute for human-human interaction (which is readily available online, anyway). Incidentally, AI could be used to form groups of online language learners to carry out communicative tasks – ‘the aim might be to design a grouping of students all at a similar cognitive level and of similar interests, or one where the participants bring different but complementary knowledge and skills’ (Luckin, R., Holmes, W., Griffiths, M. & Forceir, L.B. 2016. Intelligence Unleashed: An argument for AI in Education. London: Pearson, p.26).

Predictions about the impact of technology on education have a tendency to be made by people with a vested interest in the technologies. Edison was a businessman who had invested heavily in motion pictures. Donald Clark is an edtech entrepreneur whose company, Wildfire, uses AI in online learning programs. Stephen Heppell is executive chairman of LP+ who are currently developing a Chinese language learning community for 20 million Chinese school students. The reporting of AIED is almost invariably in websites that are paid for, in one way or another, by edtech companies. Predictions need, therefore, to be treated sceptically. Indeed, the safest prediction we can make about hyped educational technologies is that inflated expectations will be followed by disillusionment, before the technology finds a smaller niche.