Part 2: simple models of adaptive learning

Posted: January 24, 2014 in A guide to adaptive learning
Tags: , , , , , , , , , ,

‘Adaptive learning’ can mean slightly different things to different people. According to one provider of adaptive learning software (Smart Sparrow, it is ‘an online learning and teaching medium that uses an Intelligent Tutoring System to adapt online learning to the student’s level of knowledge. Adaptive eLearning provides students with customised educational content and the unique feedback that they need, when they need it.’ Essentially, it is software that analyzes the work that a student is doing online, and tailors further learning tasks to the individual learner’s needs (as analyzed by the software).

A relatively simple example of adaptive language learning is Duolingo, a free online service that currently offers seven languages, including English ( ), with over 10 million users in November 2013. Learners progress through a series of translation, dictation and multiple choice exercises that are organised into a ‘skill tree’ of vocabulary and grammar areas. Because translation plays such a central role, the program is only suitable for speakers of one of the languages on offer in combination with one of the other languages on offer. Duolingo’s own blog describes the approach in the following terms: ‘Every time you finish a Duolingo lesson, translation, test, or practice session, you provide valuable data about what you know and what you’re struggling with. Our system uses this info to plan future lessons and select translation tasks specifically for your skills and needs. Similar to how an online store uses your previous purchases to customize your shopping experience, Duolingo uses your learning history to customize your learning experience’ ( skilltree

Example of a ‘skill tree’ from

For anyone with a background in communicative language teaching, the experience can be slightly surreal. Examples of sentences that need to be translated include: The dog eats the bird, the boy has a cow, and the fly is eating bread. The system allows you to compete and communicate with other learners, and to win points and rewards (see ‘Gamification’ next post).

Duolingo describes its crowd-sourced, free, adaptive approach as ‘pretty unique’, but uniquely unique it is not. It is essentially a kind of memory trainer, and there are a number available on the market. One of the most well-known is Cerego’s cloud-based iKnow!, which describes itself as a ‘memory management platform’. Particularly strong in Japan, corporate and individual customers pay a monthly subscription to access its English, Chinese and Japanese language programs. A free trial of some of the products is available at  and I experimented with their ‘Erudite English’ program. This presented a series of words which included ‘defalcate’, ‘fleer’ and ‘kvetch’ through English-only definitions, followed by multiple choice and dictated gap-fill exercises. As with Duolingo, there seemed to be no obvious principle behind the choice of items, and example sentences included things like ‘Michael arrogates a slice of carrot cake, unbeknownst to his sister,’ or ‘She found a place in which to posit the flowerpot.’ Based on a user’s performance, Cerego’s algorithms decide which items will be presented, and select the frequency and timing of opportunities for review. The program can be accessed through ordinary computers, as well as iPhone and Android apps. The platform has been designed in such a way as to allow other content to be imported, and then presented and practised in a similar way.

In a similar vein, the Rosetta Stone software also uses spaced repetition to teach grammar and vocabulary. It describes its adaptive learning as ‘Adaptive Recall™’ According to their website, this provides review activities for each lesson ‘at intervals that are determined by your performance in that review. Exceed the program’s expectations for you and the review gets pushed out further. Fall short and you’ll see it sooner. The program gives you a likely date and automatically notifies you when it’s time to take the review again’. Rosetta Stone has won numerous awards and claims that over 20,000 educational institutions around the world have formed partnerships with them. These include the US military, the University of Barcelona and Harrogate Grammar school in the UK ( ).

Slightly more sophisticated than the memory-trainers described above is the GRE (the Graduate Record Examinations, a test for admission into many graduate schools in the US) online preparation program that is produced by Barron’s ( ). Although this is not an English language course, it provides a useful example of how simple adaptive learning programs can be taken a few steps further. At the time of writing, it is possible to do a free trial, and this gives a good taste of adaptive learning. Barron’s highlights the way that their software delivers individualized study programs: it is not, they say, a case of ‘one size fits all’. After entering the intended test date, the intended number of hours of study, and a simple self-evaluation of different reasoning skills, a diagnostic test completes the information required to set up a personalized ‘prep plan’. This determines the lessons you will be given. As you progress through the course, the ‘prep plan’ adapts to the work that you do, comparing your performance to other students who have taken the course. Measuring your progress and modifying your ‘skill profile’, the order of the lessons and the selection of the 1000+ practice questions can change.

  1. Daniel says:

    Hi Phillip,
    Interesting you’re focusing on this – it’s a huge area of language learning that our little branch of ELT has largely ignored (haven’t we left most homestudy methods alone over the last n years?). I had a go at Duolingo the other day and, while I enjoyed and found useful the translation activities, did question their choice of language – not exactly high surrender value, is it?!

    I’m just wondering what your interest in all of this is – it would be good to know where you’re coming from. Can we expect the Kerr-ang! English app for our Androids soon?

    • philipjkerr says:

      Hi Daniel
      My interest in this stems from two things. Firstly, I had been working, until recently, on a writing project that was going to be geared around an adaptive ecosystem. The project died, but while I was working on it, I did my best to find out as much as I could about adaptive learning systems. Secondly, as a writer, as a trainer, I am concerned about the direction that the major publishers are going in. Not only because it provides a handy excuse to abolish royalties and put us all on minimum-wage fees. But also because it flies in the face of almost everything we have learnt about L2 acquisition and language teaching in the last thirty years. I’ll get on to this in later posts.

      • Daniel says:

        I remember my favourite from Duolingo – it was: ‘El gato duerme sobre el mono’. I played along with it. ‘The cat is sleeping on the monkey’ was my answer, for which I got an ‘incorrect’. Similarly, ‘Oigo animales’ prompted me to translate ‘I can hear animals’, which wasn’t what the app was expecting. My attempts to impose meaning on this computer-generated crap (in the first, I assumed the ‘speaker’ was describing an unusual scene rather than telling us the place the cat normally sleeps, and the second, I assumed, was about Dr. Doolittle superpowers) were futile and batted down with a negative response. Like Scott (see below), I adapted to it, and learnt to give wrong answers. For a while, anyway. Then I gave up.

      • philipjkerr says:

        Thomson and Martinet strike back!

      • PeterLoveday says:

        Thanks Philip. All very ominous, and sad that publishers pick up the wrong ball and run in the wrong direction. Is technology so blinding? Your comment here about publisher motivation says it all really, .. and as Gavin says below; “more profit out of less investment”.

  2. Ceri Jones says:

    Very useful, Philip, thanks. Though I did have to posit my coffee cup at one point as I spluttered out a dry laugh.

  3. I’m so pleased you embarked on this, Philip, not least because you save me the bother of trying out these programs for myself. Although I did use Duolingo for a bit as part of my Spanish ‘de-fossilization’ project, because I was intrigued by their ‘mission statement’ re crowd-sourcing the translation of texts online, including the claim that the whole of Spanish wikipedia could be translated into English in just 80 hours if X tens of thousands of students of Spanish put their minds to it – I can’t remember the exact figures. I liked the idea of translating real texts and getting feedback, but I never graduated from ‘the fly is eating bread’ phase, so I gave up.

    Will you be making the point that these adaptive learning tools are simply the most recent manifestation of what used to be called ‘programmed instruction’, as described by Skinner in 1954? ‘The device makes it possible to present carefully designed material in which one problem can depend upon the answer to the preceding and where therefore the most progress to an eventually complex repertoire can be made’ (quoted in Selwyn 2011, Education and Technology: Key Issues & Debates).

    The only substantive difference between programmed instruction and adaptive learning seems to be be that the ‘adaptive’ functionality is much more rapid and sophisticated – but still constrained by the fact that the program (like all educational software) is still a program, and, lacking intersubjectivity, cannot ‘read’ your communicative intentions. It doesn’t know what you want to mean, in short.

    In that sense, I wonder who or what is being adaptive? The ‘teacher’ or the learner? As I worked my way through the Duolingo tasks, I got better at them, not so much because I was learning anything linguistic, but because I was learning how the damned thing worked. I was adapting to it.

    In that sense, I was having turn myself into a machine, ‘a rude mechanical’, like the computer. As one commentator puts it:

    ‘Because computers cannot come to us and meet us in our world, we must continue to adjust our world and bring ourselves to them. We will define and regiment our lives, including our social lives and our perceptions of our selves, in ways that are conducive to what a computer can “understand”. Their dumbness will become ours.’

    Auerbach, D. 2012. ‘The stupidity of computers’ n+1 magazine, Issue 13.

    • philipjkerr says:

      I had a similar experience to you with Duolingo. As a matter of fact, it was a while ago when I was staying in Barcelona. I started translating real texts from an early stage, (1) because I was getting bored with ‘the horse likes strawberries’, etc., and (2) because I wanted to win some bonus points. I returned to Duolingo briefly a few months ago, but gave up fast. I’m now reading and translating 19th century German newspapers in order to improve my German. Much more fun (for me!) and the language is not less bizarre than what I’d been getting with Duolingo.
      Yes, I will be getting on to a more critical look at the whole business in later posts. I’ll be comparing, for example, Knewton’s ‘granularization’ with Grammar McNuggets. For the moment, though, I’m trying to remain mostly descriptive. But, yes, the ‘adaptivity’ of these programmes is somehow reminiscent of the ‘interactivity’ of IWBs: hooray words that don’t quite mean what they appear to mean, and applied to technologies, which, we can be pretty sure, will seem very outdated one of these days.

  4. Philip,

    Really enjoying this new outing, as much as I did the translation one a couple of years back. Adaptive learning seems a retrograde step to me, an abomination in both teaching and educational technology terms. It takes everything that can be (and often is) creative about technology in teaching and learning and leaves it lying in a dark corner in favour of a binary measuring of the whole process. Relying on 0s and 1s to understand the nuances of human communication and learning is a folly which should never have got this far.

    The sad truth, as you know, is that every major publisher is looking this way now – I presume you saw the four-parter over here: ? What are our chances of playing outside this in the long term?

    And, what was it like working on the inside of one of these projects, before it got axed? Did you adapt to love adaptive learning?


    • philipjkerr says:

      In the long term, I imagine things will change, but by long term, I mean ten or so years from now. It won’t really work, but huge numbers of people will have bought into it. And so some institutions, with more money, will want to differentiate themselves from the rest, and one obvious way to do that is to prioritise F2F. But in the meantime, nobody should underestimate the full force of the adaptive learning lobby that will be hitting them soon. As for working inside … I can’t really say. Things were only beginning. The axe came when the money men realised that investments on the software meant that they had to cut back on what they cutely call the ‘content’. Basically, the way it’s going now is that any old shit content will do, so long as it’s cheap. Blind the punters with technology.

  5. Looking at the Smart [sic] Sparrow website, I can barely contain my gag reflex.

    For example: “Adaptive eLearning Platform provides teachers with a window into their students’ learning for the lessons they’ve created. Online analytics provide actionable insights into what students know, what misconceptions they may have, and how they are interacting with content. This feature allows teachers to continuously adapt and improve their lessons.”

    As if teachers have never been able to do this? As if an algorithm can somehow do it better?

    I feel an ‘actionable insight’ coming on!

  6. huwjarvis says:

    Arguably this is but one of the consequences of describing and investigating practice within a CALL framework. I’ve said it before and will be saying it again soon (forthcoming with Krashen) time to move to Mobile Assisted Language Use

    • Huw,

      I know you never miss an opportunity to push that acronym, but this is nothing of the sort. What this is, is one of the consequences of publishers trying to eke more and more profit out of less and less investment. It’s a consequence of companies not trusting teachers to do the job, or make them enough money from doing it. This is nothing to do with CALL or TELL or MALU or any other acronym. This is mostly greed, and a desire to take over control of what, to this day, has mostly been about people.


      • huwjarvis says:

        Your point is direct and well made, as ever. It was the focus on the explicit tutorial role of technology which was behind my thinking. If we fail to take a broader view this is one path that CALL leads us down, but as I also acknowledge this is “arguably” 🙂 the case.

  7. Jill Hadfield says:

    New to adaptive learning but horrified at what I’m hearing from you?

  8. blogefl says:

    Very interesting reading (blog posts and comments) indeed, but I wonder whether this is now a steam-roller that none of us will be able to stop and which will end up being used by the general language learning population whether we like it or not, in which case some of us will have to take sides and work from the inside to influence how it evolves, or work outside of adaptive learning and try to prevent it from taking hold.

    • philipjkerr says:

      I’ll be getting on to the nature of this steam-roller and why it may be more or less unstoppable in later posts. As for influencing it from inside, that may not be so easy, either. Adaptive learning is very much part of the world of big data / analytics, much more so than it is part of the world of education. In this world, ‘subject-matter specialists will not go away, but they will have to content with what the big-data analysis says. This will force an adjustment to traditional ideas of management, decision-making, human resources and education’ (Viktor Mayer-Schonberger and Kenneth Cukier, Big Data, London: John Murray, 2013, p.16).

  9. Marie Duffy says:

    Fascinating information posted above- a lot of food for thought as a Language Teacher. I really liked the idea of Duolingo- tailor made education at no cost is a very attractive option for learners. I also think that the competitive aspect of adaptive learning programmes is fantastic. Competing with other students and getting ‘points’ is very motivating. Loved this article!

  10. David says:

    An interesting article.Definitely something to think about. But I agree with the comments made by Scott Thornbury and that adaptive elearning platforms don’t contribute anything new that teachers aren’t already contributing in the classroom at present. It all seems like more of a gimmick than anything else and has been designed with ‘large sales’ of the software in mind.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s