Big data, learning analytics and language learning / teaching

The use of big data and analytics in education continues to grow.

A vast apparatus of measurement is being developed to underpin national education systems, institutions and the actions of the individuals who occupy them. […] The presence of digital data and software in education is being amplified through massive financial and political investment in educational technologies, as well as huge growth in data collection and analysis in policymaking practices, extension of performance measurement technologies in the management of educational institutions, and rapid expansion of digital methodologies in educational research. To a significant extent, many of the ways in which classrooms function, educational policy departments and leaders make decisions, and researchers make sense of data, simply would not happen as currently intended without the presence of software code and the digital data processing programs it enacts. (Williamson, 2017: 4)

The most common and successful use of this technology so far has been in the identification of students at risk of dropping out of their courses (Jørno & Gynther, 2018: 204). The kind of analytics used in this context may be called ‘academic analytics’ and focuses on educational processes at the institutional level or higher (Gelan et al, 2018: 3). However, ‘learning analytics’, the capture and analysis of learner and learning data in order to personalize learning ‘(1) through real-time feedback on online courses and e-textbooks that can ‘learn’ from how they are used and ‘talk back’ to the teacher, and (2) individualization and personalization of the educational experience through adaptive learning systems that enable materials to be tailored to each student’s individual needs through automated real-time analysis’ (Mayer-Schönberger & Cukier, 2014) has become ‘the main keyword of data-driven education’ (Williamson, 2017: 10). See my earlier posts on this topic here and here and here.

Near the start of Mayer-Schönberger and Cukier’s enthusiastic sales pitch (Learning with Big Data: The Future of Education) for the use of big data in education, there is a discussion of Duolingo. They quote Luis von Ahn, the founder of Duolingo, as saying ‘there has been little empirical work on what is the best way to teach a foreign language’. This is so far from the truth as to be laughable. Von Ahn’s comment, along with the Duolingo product itself, is merely indicative of a lack of awareness of the enormous amount of research that has been carried out. But what could the data gleaned from the interactions of millions of users with Duolingo tell us of value? The example that is given is the following. Apparently, ‘in the case of Spanish speakers learning English, it’s common to teach pronouns early on: words like “he,” “she,” and “it”.’ But, Duolingo discovered, ‘the term “it” tends to confuse and create anxiety for Spanish speakers, since the word doesn’t easily translate into their language […] Delaying the introduction of “it” until a few weeks later dramatically improves the number of people who stick with learning English rather than drop out.’ Was von Ahn unaware of the decades of research into language transfer effects? Did von Ahn (who grew up speaking Spanish in Guatemala) need all this data to tell him that English personal pronouns can cause problems for Spanish learners of English? Was von Ahn unaware of the debates concerning the value of teaching isolated words (especially grammar words!)?

The area where little empirical research has been done is not in different ways of learning another language: it is in the use of big data and learning analytics to assist language learning. Claims about the value of these technologies in language learning are almost always speculative – they are based on comparison to other school subjects (especially, mathematics). Gelan et al (2018: 2), who note this lack of research, suggest that ‘understanding language learner behaviour could provide valuable insights into task design for instructors and materials designers, as well as help students with effective learning strategies and personalised learning pathways’ (my italics). Reinders (2018: 81) writes ‘that analysis of prior experiences with certain groups or certain courses may help to identify key moments at which students need to receive more or different support. Analysis of student engagement and performance throughout a course may help with early identification of learning problems and may prompt early intervention’ (italics added). But there is some research out there, and it’s worth having a look at. Most studies that have collected learner-tracking data concern glossary use for reading comprehension and vocabulary retention (Gelan et al, 2018: 5), but a few have attempted to go further in scope.

Volk et al (2015) looked at the behaviour of the 20,000 students per day using the platform which accompanies ‘More!’ (Gerngross et al. 2008) to do their English homework for Austrian lower secondary schools. They discovered that

• the exercises used least frequently were those that are located further back in the course book
• usage is highest from Monday to Wednesday, declining from Thursday, with a rise again on Sunday
• most interaction took place between 3:00 and 5:00 pm.
• repetition of exercises led to a strong improvement in success rate
• students performed better on multiple choice and matching exercises than they did where they had to produce some language

The authors of this paper conclude by saying that ‘the results of this study suggest a number of new avenues for research. In general, the authors plan to extend their analysis of exercise results and applied exercises to the population of all schools using the online learning platform more-online.at. This step enables a deeper insight into student’s learning behaviour and allows making more generalizing statements.’ When I shared these research findings with the Austrian lower secondary teachers that I work with, their reaction was one of utter disbelief. People get paid to do this research? Why not just ask us?

More useful, more actionable insights may yet come from other sources. For example, Gu Yueguo, Pro-Vice-Chancellor of the Beijing Foreign Studies University has announced the intention to set up a national Big Data research center, specializing in big data-related research topics in foreign language education (Yu, 2015). Meanwhile, I’m aware of only one big research project that has published its results. The EC Erasmus+ VITAL project (Visualisation Tools and Analytics to monitor Online Language Learning & Teaching) was carried out between 2015 and 2017 and looked at the learning trails of students from universities in Belgium, Britain and the Netherlands. It was discovered (Gelan et al, 2015) that:

• students who did online exercises when they were supposed to do them were slightly more successful than those who were late carrying out the tasks
• successful students logged on more often, spent more time online, attempted and completed more tasks, revisited both exercises and theory pages more frequently, did the work in the order in which it was supposed to be done and did more work in the holidays
• most students preferred to go straight into the assessed exercises and only used the theory pages when they felt they needed to; successful students referred back to the theory pages more often than unsuccessful students
• students made little use of the voice recording functionality
• most online activity took place the day before a class and the day of the class itself

EU funding for this VITAL project amounted to 274,840 Euros[1]. The technology for capturing the data has been around for a long time. In my opinion, nothing of value, or at least nothing new, has been learnt. Publishers like Pearson and Cambridge University Press who have large numbers of learners using their platforms have been capturing learning data for many years. They do not publish their findings and, intriguingly, do not even claim that they have learnt anything useful / actionable from the data they have collected. Sure, an exercise here or there may need to be amended. Both teachers and students may need more support in using the more open-ended functionalities of the platforms (e.g. discussion forums). But are they getting ‘unprecedented insights into what works and what doesn’t’ (Mayer-Schönberger & Cukier, 2014)? Are they any closer to building better pedagogies? On the basis of what we know so far, you wouldn’t want to bet on it.

It may be the case that all the learning / learner data that is captured could be used in some way that has nothing to do with language learning. Show me a language-learning app developer who does not dream of monetizing the ‘behavioural surplus’ (Zuboff, 2018) that they collect! But, for the data and analytics to be of any value in guiding language learning, it must lead to actionable insights. Unfortunately, as Jørno & Gynther (2018: 198) point out, there is very little clarity about what is meant by ‘actionable insights’. There is a danger that data and analytics ‘simply gravitates towards insights that confirm longstanding good practice and insights, such as “students tend to ignore optional learning activities … [and] focus on activities that are assessed” (Jørno & Gynther, 2018: 211). While this is happening, the focus on data inevitably shapes the way we look at the object of study (i.e. language learning), ‘thereby systematically excluding other perspectives’ (Mau, 2019: 15; see also Beer, 2019). The belief that tech is always the solution, that all we need is more data and better analytics, remains very powerful: it’s called techno-chauvinism (Broussard, 2018: 7-8).

References

Beer, D. 2019. The Data Gaze. London: Sage

Broussard, M. 2018. Artificial Unintelligence. Cambridge, Mass.: MIT Press

Gelan, A., Fastre, G., Verjans, M., Martin, N., Jansenswillen, G., Creemers, M., Lieben, J., Depaire, B. & Thomas, M. 2018. ‘Affordances and limitations of learning analytics for computer­assisted language learning: a case study of the VITAL project’. Computer Assisted Language Learning. pp. 1­26. http://clok.uclan.ac.uk/21289/

Gerngross, G., Puchta, H., Holzmann, C., Stranks, J., Lewis-Jones, P. & Finnie, R. 2008. More! 1 Cyber Homework. Innsbruck, Austria: Helbling

Jørno, R. L. & Gynther, K. 2018. ‘What Constitutes an “Actionable Insight” in Learning Analytics?’ Journal of Learning Analytics 5 (3): 198 – 221

Mau, S. 2019. The Metric Society. Cambridge: Polity Press

Mayer-Schönberger, V. & Cukier, K. 2014. Learning with Big Data: The Future of Education. New York: Houghton Mifflin Harcourt

Reinders, H. 2018. ‘Learning analytics for language learning and teaching’. JALT CALL Journal 14 / 1: 77 – 86 https://files.eric.ed.gov/fulltext/EJ1177327.pdf

Volk, H., Kellner, K. & Wohlhart, D. 2015. ‘Learning Analytics for English Language Teaching.’ Journal of Universal Computer Science, Vol. 21 / 1: 156-174 http://www.jucs.org/jucs_21_1/learning_analytics_for_english/jucs_21_01_0156_0174_volk.pdf

Williamson, B. 2017. Big Data in Education. London: Sage

Yu, Q. 2015. ‘Learning Analytics: The next frontier for computer assisted language learning in big data age’ SHS Web of Conferences, 17 https://www.shs-conferences.org/articles/shsconf/pdf/2015/04/shsconf_icmetm2015_02013.pdf

Zuboff, S. 2019. The Age of Surveillance Capitalism. London: Profile Books

 

[1] See https://ec.europa.eu/programmes/erasmus-plus/sites/erasmusplus2/files/ka2-2015-he_en.pdf

Analytics and ELT course materials

Back in December 2013, in an interview with eltjam , David Liu, COO of the adaptive learning company, Knewton, described how his company’s data analysis could help ELT publishers ‘create more effective learning materials’. He focused on what he calls ‘content efficacy[i]’ (he uses the word ‘efficacy’ five times in the interview), a term which he explains below:

A good example is when we look at the knowledge graph of our partners, which is a map of how concepts relate to other concepts and prerequisites within their product. There may be two or three prerequisites identified in a knowledge graph that a student needs to learn in order to understand a next concept. And when we have hundreds of thousands of students progressing through a course, we begin to understand the efficacy of those said prerequisites, which quite frankly were made by an author or set of authors. In most cases they’re quite good because these authors are actually good in what they do. But in a lot of cases we may find that one of those prerequisites actually is not necessary, and not proven to be useful in achieving true learning or understanding of the current concept that you’re trying to learn. This is interesting information that can be brought back to the publisher as they do revisions, as they actually begin to look at the content as a whole.

One commenter on the post, Tom Ewens, found the idea interesting. It could, potentially, he wrote, give us new insights into how languages are learned much in the same way as how corpora have given us new insights into how language is used. Did Knewton have any plans to disseminate the information publicly, he asked. His question remains unanswered.

At the time, Knewton had just raised $51 million (bringing their total venture capital funding to over $105 million). Now, 16 months later, Knewton have launched their new product, which they are calling Knewton Content Insights. They describe it as the world’s first and only web-based engine to automatically extract statistics comparing the relative quality of content items — enabling us to infer more information about student proficiency and content performance than ever before possible.

The software analyses particular exercises within the learning content (and particular items within them). It measures the relative difficulty of individual items by, for example, analysing how often a question is answered incorrectly and how many tries it takes each student to answer correctly. It also looks at what they call ‘exhaustion’ – how much content students are using in a particular area – and whether they run out of content. The software can correlate difficulty with exhaustion. Lastly, it analyses what they call ‘assessment quality’ – how well  individual questions assess a student’s understanding of a topic.

Knewton’s approach is premised on the idea that learning (in this case language learning) can be broken down into knowledge graphs, in which the information that needs to be learned can be arranged and presented hierarchically. The ‘granular’ concepts are then ‘delivered’ to the learner, and Knewton’s software can optimise the delivery. The first problem, as I explored in a previous post, is that language is a messy, complex system: it doesn’t lend itself terribly well to granularisation. The second problem is that language learning does not proceed in a linear, hierarchical way: it is also messy and complex. The third is that ‘language learning content’ cannot simply be delivered: a process of mediation is unavoidable. Are the people at Knewton unaware of the extensive literature devoted to the differences between synthetic and analytic syllabuses, of the differences between product-oriented and process-oriented approaches? It would seem so.

Knewton’s ‘Content Insights’ can only, at best, provide some sort of insight into the ‘language knowledge’ part of any learning content. It can say nothing about the work that learners do to practise language skills, since these are not susceptible to granularisation: you simply can’t take a piece of material that focuses on reading or listening and analyse its ‘content efficacy at the concept level’. Because of this, I predicted (in the post about Knowledge Graphs) that the likely focus of Knewton’s analytics would be discrete item, sentence-level grammar (typically tenses). It turns out that I was right.

Knewton illustrate their new product with screen shots such as those below.

 

 

 

 

 

 

 

 

 

 

 

 

They give a specific example of the sort of questions their software can answer. It is: do students generally find the present simple tense easier to understand than the present perfect tense? Doh!

It may be the case that Knewton Content Insights might optimise the presentation of this kind of grammar, but optimisation of this presentation and practice is highly unlikely to have any impact on the rate of language acquisition. Students are typically required to study the present perfect at every level from ‘elementary’ upwards. They have to do this, not because the presentation in, say, Headway, is not optimised. What they need is to spend a significantly greater proportion of their time on ‘language use’ and less on ‘language knowledge’. This is not just my personal view: it has been extensively researched, and I am unaware of any dissenting voices.

The number-crunching in Knewton Content Insights is unlikely, therefore, to lead to any actionable insights. It is, however, very likely to lead (as writer colleagues at Pearson and other publishers are finding out) to an obsession with measuring the ‘efficacy’ of material which, quite simply, cannot meaningfully be measured in this way. It is likely to distract from much more pressing issues, notably the question of how we can move further and faster away from peddling sentence-level, discrete-item grammar.

In the long run, it is reasonable to predict that the attempt to optimise the delivery of language knowledge will come to be seen as an attempt to tackle the wrong question. It will make no significant difference to language learners and language learning. In the short term, how much time and money will be wasted?

[i] ‘Efficacy’ is the buzzword around which Pearson has built its materials creation strategy, a strategy which was launched around the same time as this interview. Pearson is a major investor in Knewton.

Datapalooza

Jose Ferreira, the fast-talking sales rep-in-chief of Knewton, likes to dazzle with numbers. In a 2012 talk hosted by the US Department of Education, Ferreira rattles off the stats: So Knewton students today, we have about 125,000, 180,000 right now, by December it’ll be 650,000, early next year it’ll be in the millions, and next year it’ll be close to 10 million. And that’s just through our Pearson partnership. For each of these students, Knewton gathers millions of data points every day. That, brags Ferreira, is five orders of magnitude more data about you than Google has. … We literally have more data about our students than any company has about anybody else about anything, and it’s not even close. With just a touch of breathless exaggeration, Ferreira goes on: We literally know everything about what you know and how you learn best, everything.

The data is mined to find correlations between learning outcomes and learning behaviours, and, once correlations have been established, learning programmes can be tailored to individual students. Ferreira explains: We take the combined data problem all hundred million to figure out exactly how to teach every concept to each kid. So the 100 million first shows up to learn the rules of exponents, great let’s go find a group of people who are psychometrically equivalent to that kid. They learn the same ways, they have the same learning style, they know the same stuff, because Knewton can figure out things like you learn math best in the morning between 8:40 and 9:13 am. You learn science best in 42 minute bite sizes the 44 minute mark you click right, you start missing questions you would normally get right.

The basic premise here is that the more data you have, the more accurately you can predict what will work best for any individual learner. But how accurate is it? In the absence of any decent, independent research (or, for that matter, any verifiable claims from Knewton), how should we respond to Ferreira’s contribution to the White House Education Datapalooza?

A new book by Stephen Finlay, Predictive Analytics, Data Mining and Big Data (Palgrave Macmillan, 2014) suggests that predictive analytics are typically about 20 – 30% more accurate than humans attempting to make the same judgements. That’s pretty impressive and perhaps Knewton does better than that, but the key thing to remember is that, however much data Knewton is playing with, and however good their algorithms are, we are still talking about predictions and not certainties. If an adaptive system could predict with 90% accuracy (and the actual figure is typically much lower than that) what learning content and what learning approach would be effective for an individual learner, it would still mean that it was wrong 10% of the time. When this is scaled up to the numbers of students that use Knewton software, it means that millions of students are getting faulty recommendations. Beyond a certain point, further expansion of the data that is mined is unlikely to make any difference to the accuracy of predictions.

A further problem identified by Stephen Finlay is the tendency of people in predictive analytics to confuse correlation and causation. Certain students may have learnt maths best between 8.40 and 9.13, but it does not follow that they learnt it best because they studied at that time. If strong correlations do not involve causality, then actionable insights (such as individualised course design) can be no more than an informed gamble.

Knewton’s claim that they know how every student learns best is marketing hyperbole and should set alarm bells ringing. When it comes to language learning, we simply do not know how students learn (we do not have any generally accepted theory of second language acquisition), let alone how they learn best. More data won’t help our theories of learning! Ferreira’s claim that, with Knewton, every kid gets a perfectly optimized textbook, except it’s also video and other rich media dynamically generated in real time is equally preposterous, not least since the content of the textbook will be at least as significant as the way in which it is ‘optimized’. And, as we all know, textbooks have their faults.

Cui bono? Perhaps huge data and predictive analytics will benefit students; perhaps not. We will need to wait and find out. But Stephen Finlay reminds us that in gold rushes (and internet booms and the exciting world of Big Data) the people who sell the tools make a lot of money. Far more strike it rich selling picks and shovels to prospectors than do the prospectors. Likewise, there is a lot of money to be made selling Big Data solutions. Whether the buyer actually gets any benefit from them is not the primary concern of the sales people. (p.16/17) Which is, perhaps, one of the reasons that some sales people talk so fast.

Adaptive reading?

There is a lot that technology can do to help English language learners develop their reading skills. The internet makes it possible for learners to read an almost limitless number of texts that will interest them, and these texts can evaluated for readability and, therefore, suitability for level (see here for a useful article). RSS opens up exciting possibilities for narrow reading and the positive impact of multimedia-enhanced texts was researched many years ago. There are good online bilingual dictionaries and other translation tools. There are apps that go with graded readers (see this review in the Guardian) and there are apps that can force you to read at a certain speed. And there is more. All of this could very effectively be managed on a good learning platform.

Could adaptive software add another valuable element to reading skills development?

Adaptive reading programs are spreading in the US in primary education, and, with some modifications, could be used in ELT courses for younger learners and for those who do not have the Roman alphabet. One of the most well-known has been developed by Lexia Learning®, a company that won a $500,000 grant from the Gates Foundation last year. Lexia Learning® was bought by Rosetta Stone® for $22.5 million in June 2013.

One of their products, Lexia Reading Core5, ‘provides explicit, systematic, personalized learning in the six areas of reading instruction, and delivers norm-referenced performance data and analysis without interrupting the flow of instruction to administer a test. Designed specifically to meet the Common Core and the most rigorous state standards, this research-proven, technology-based approach accelerates reading skills development, predicts students’ year-end performance and provides teachers data-driven action plans to help differentiate instruction’.

The predictable claim that it is ‘research-proven’ has not convinced everyone. Richard Allington, a professor of literacy studies at the University of Tennessee and a past president of both the International Reading Association and the National Reading Association, has said that all the companies that have developed this kind of software ‘come up with evidence – albeit potential evidence — that kids could improve their abilities to read by using their product. It’s all marketing. They’re selling a product. Lexia is one of these programs. But there virtually are no commercial programs that have any solid, reliable evidence that they improve reading achievement.’[1] He has argued that the $12 million that has been spent on the Lexia programs would have been better spent on a national program, developed at Ohio State University, that matches specially trained reading instructors with students known to have trouble learning to read.

But what about ELT? For an adaptive program like Lexia’s to work, reading skills need to be broken down in a similar way to the diagram shown above. Let’s get some folk linguistics out of the way first. The sub-skills of reading are not skimming, scanning, inferring meaning from context, etc. These are strategies that readers adopt voluntarily in order to understand a text better. If a reader uses these strategies in their own language, they are likely to transfer these strategies to their English reading. It seems that ELT instruction in strategy use has only limited impact, although this kind of training may be relevant to preparation for exams. This insight is taking a long time to filter down to course and coursebook design, but there really isn’t much debate[2]. Any adaptive ELT reading program that confuses reading strategies with reading sub-skills is going to have big problems.

What, then, are the sub-skills of reading? In what ways could reading be broken down into a skill tree so that it is amenable to adaptive learning? Researchers have provided different answers. Munby (1978), for example, listed 19 reading microskills, Heaton (1988) listed 14. However, a bigger problem is that other researchers (e.g. Lunzer 1979, Rost 1993) have failed to find evidence that distinct sub-skills actually exist. While it is easier to identify sub-skills for very low level readers (especially for those whose own language is very different from English), it is simply not possible to do so for higher levels.

Reading in another language is a complex process which involves both top-down and bottom-up strategies, is intimately linked to vocabulary knowledge and requires the activation of background, cultural knowledge. Reading ability, in the eyes of some researchers, is unitary or holistic. Others prefer to separate things into two components: word recognition and comprehension[3]. Either way, a consensus is beginning to emerge that teachers and learners might do better to focus on vocabulary extension (and this would include extensive reading) than to attempt to develop reading programs that assume the multidivisible nature of reading.

All of which means that adaptive learning software and reading skills in ELT are unlikely bedfellows. To be sure, an increased use of technology (as described in the first paragraph of this post) in reading work will generate a lot of data about learner behaviours. Analysis of this data may lead to actionable insights, and it may not! It will be interesting to find out.

 

[1] http://www.khi.org/news/2013/jun/17/budget-proviso-reading-program-raises-questions/

[2] See, for example, Walter, C. & M. Swan. 2008. ‘Teaching reading skills: mostly a waste of time?’ in Beaven, B. (ed.) IATEFL 2008 Exeter Conference Selections. (Canterbury: IATEFL). Or go back further to Alderson, J. C. 1984 ‘Reading in a foreign language: a reading problem or a language problem?’ in J.C. Alderson & A. H. Urquhart (eds.) Reading in a Foreign Language (London: Longman)

[3] For a useful summary of these issues, see ‘Reading abilities and strategies: a short introduction’ by Feng Liu (International Education Studies 3 / 3 August 2010) www.ccsenet.org/journal/index.php/ies/article/viewFile/6790/5321

Part 8: theory, research and practice

One could be forgiven for thinking that there are no problems associated with adaptive learning in ELT. Type the term into a search engine and you’ll mostly come up with enthusiasm or sales talk. There are, however, a number of reasons to be deeply skeptical about the whole business. In the post after this, I will be considering the political background.

1. Learning theory

Jose Fereira, the CEO of Knewton, spoke, in an interview with Digital Journal[1] in October 2009, about getting down to the ‘granular level’ of learning. He was referencing, in an original turn of phrase, the commonly held belief that learning is centrally concerned with ‘gaining knowledge’, knowledge that can be broken down into very small parts that can be put together again. In this sense, the adaptive learning machine is very similar to the ‘teaching machine’ of B.F. Skinner, the psychologist who believed that learning was a complex process of stimulus and response. But how many applied linguists would agree, firstly, that language can be broken down into atomised parts (rather than viewed as a complex, dynamic system), and, secondly, that these atomised parts can be synthesized in a learning program to reform a complex whole? Human cognitive and linguistic development simply does not work that way, despite the strongly-held contrary views of ‘folk’ theories of learning (Selwyn Education and Technology 2011, p.3).

Furthermore, even if an adaptive system delivers language content in personalized and interesting ways, it is still premised on a view of learning where content is delivered and learners receive it. The actual learning program is not personalized in any meaningful way: it is only the way that it is delivered that responds to the algorithms. This is, again, a view of learning which few educationalists (as opposed to educational leaders) would share. Is language learning ‘simply a technical business of well managed information processing’ or is it ‘a continuing process of ‘participation’ (Selwyn, Education and Technology 2011, p.4)?

Finally, adaptive learning is also premised on the idea that learners have particular learning styles, that these can be identified by the analytics (even if they are not given labels), and that actionable insights can be gained from this analysis (i.e. the software can decide on the most appropriate style of content delivery for an individual learner). Although the idea that teaching programs can be modified to cater to individual learning styles continues to have some currency among language teachers (e.g. those who espouse Neuro-Linguistic Programming or Multiple Intelligences Theory), it is not an idea that has much currency in the research community.

It might be the case that adaptive learning programs will work with some, or even many, learners, but it would be wise to carry out more research (see the section on Research below) before making grand claims about its efficacy. If adaptive learning can be shown to be more effective than other forms of language learning, it will be either because our current theories of language learning are all wrong, or because the learning takes place despite the theory, (and not because of it).

2. Practical problems

However good technological innovations may sound, they can only be as good, in practice, as the way they are implemented. Language laboratories and interactive whiteboards both sounded like very good ideas at the time, but they both fell out of favour long before they were technologically superseded. The reasons are many, but one of the most important is that classroom teachers did not understand sufficiently the potential of these technologies or, more basically, how to use them. Given the much more radical changes that seem to be implied by the adoption of adaptive learning, we would be wise to be cautious. The following is a short, selected list of questions that have not yet been answered.

• Language teachers often struggle with mixed ability classes. If adaptive programs (as part of a blended program) allow students to progress at their own speed, the range of abilities in face-to-face lessons may be even more marked. How will teachers cope with this? Teacher – student ratios are unlikely to improve!
• Who will pay for the training that teachers will need to implement effective blended learning and when will this take place?
• How will teachers respond to a technology that will be perceived by some as a threat to their jobs and their professionalism and as part of a growing trend towards the accommodation of commercial interests (see the next post)?
• How will students respond to online (adaptive) learning when it becomes the norm, rather than something ‘different’?

3 Research

Technological innovations in education are rarely, if ever, driven by solidly grounded research, but they are invariably accompanied by grand claims about their potential. Motion pictures, radio, television and early computers were all seen, in their time, as wonder technologies that would revolutionize education (Cuban, Teachers and Machines: The Classroom Use of Technology since 1920 1986). Early research seemed to support the claims, but the passage of time has demonstrated all too clearly the precise opposite. The arrival on the scene of e-learning in general, and adaptive learning in particular, has also been accompanied by much cheer-leading and claims of research support.

Examples of such claims of research support for adaptive learning in higher education in the US and Australia include an increase in pass rates of between 7 and 18%, a decrease of between 14 and 47% in student drop-outs, and an acceleration of 25% in the time needed to complete courses[2]. However, research of this kind needs to be taken with a liberal pinch of salt. First of all, the research has usually been commissioned, and sometimes carried out, by those with vested commercial interests in positive results. Secondly, the design of the research study usually guarantees positive results. Finally, the results cannot be interpreted to have any significance beyond their immediate local context. There is no reason to expect that what happened in a particular study into adaptive learning in, say, the University of Arizona would be replicated in, say, the Universities of Amman, Astana or anywhere else. Very often, when this research is reported, the subject of the students’ study is not even mentioned, as if this were of no significance.

The lack of serious research into the effectiveness of adaptive learning does not lead us to the conclusion that it is ineffective. It is simply too soon to say, and if the examples of motion pictures, radio and television are any guide, it will be a long time before we have any good evidence. By that time, it is reasonable to assume, adaptive learning will be a very different beast from what it is today. Given the recency of this kind of learning, the lack of research is not surprising. For online learning in general, a meta-analysis commissioned by the US Department of Education (Means et al, Evaluation of Evidence-Based Practice in Online Learning 2009, p.9) found that there were only a small number of rigorous published studies, and that it was not possible to attribute any gains in learning outcomes to online or blended learning modes. As the authors of this report were aware, there are too many variables (social, cultural and economic) to compare in any direct way the efficacy of one kind of learning with another. This is as true of attempts to compare adaptive online learning with face-to-face instruction as it is with comparisons of different methodological approaches in purely face-to-face teaching. There is, however, an irony in the fact that advocates of adaptive learning (whose interest in analytics leads them to prioritise correlational relationships over causal ones) should choose to make claims about the causal relationship between learning outcomes and adaptive learning.

Perhaps, as Selwyn (Education and Technology 2011, p.87) suggests, attempts to discover the relative learning advantages of adaptive learning are simply asking the wrong question, not least as there cannot be a single straightforward answer. Perhaps a more useful critique would be to look at the contexts in which the claims for adaptive learning are made, and by whom. Selwyn also suggests that useful insights may be gained from taking a historical perspective. It is worth noting that the technicist claims for adaptive learning (that ‘it works’ or that it is ‘effective’) are essentially the same as those that have been made for other education technologies. They take a universalising position and ignore local contexts, forgetting that ‘pedagogical approach is bound up with a web of cultural assumption’ (Wiske, ‘A new culture of teaching for the 21^st century’ in Gordon, D.T. (ed.) The Digital Classroom: How Technology is Changing the Way we teach and Learn 2000, p.72). Adaptive learning might just possibly be different from other technologies, but history advises us to be cautious.

---

[1] http://www.digitaljournal.com/article/279940?utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+frc+(First+Round+Capital+News)

[2] These figures are quoted in Learning to Adapt: A Case for Accelerating Adaptive Learning in Higher Education, a booklet produced in March 2013 by Education Growth Advisors, an education consultancy firm. Their research is available at http://edgrowthadvisors.com/research/

Part 4: big data and analytics

In order to understand more complex models of adaptive learning, it is necessary to take a temporary step sideways away from the world of language learning. Businesses have long used analytics – the analysis of data to find meaningful patterns – in insurance, banking and marketing. With the exponential growth in computer processing power and memory capacity, businesses now have access to volumes of data of almost unimaginable size. This is known as ‘big data’ and has been described as ‘a revolution that will transform how we live, work and think’ (Mayer-Schönberger & Cukier, ‘Big Data’, 2013). Frequently cited examples of the potential of big data are the success of Amazon to analyze and predict buying patterns and the use of big data analysis in Barack Obama’s 2012 presidential re-election. Business commentators are all singing the same song on the subject. This will be looked at again in later posts. For the time being, it is enough to be aware of the main message. ‘The high-performing organisation of the future will be one that places great value on data and analytical exploration’ (The Economist Intelligence Unit, ‘In Search of Insight and Foresight: Getting more out of big data’ 2013, p.15). ‘Almost no sphere of business activity will remain untouched by this movement,’ (McAfee & Brynjolfsson, ‘Big Data: The Management Revolution’, Harvard Business Review (October 2012), p. 65).

With the growing bonds between business and education (another topic which will be explored later), it is unsurprising that language learning / teaching materials are rapidly going down the big data route. In comparison to what is now being developed for ELT, the data that is analyzed in the adaptive learning models I have described in an earlier post is very limited, and the algorithms used to shape the content are very simple.

The volume and variety of data and the speed of processing are now of an altogether different order. Jose Ferreira, CEO of Knewton, one of the biggest players in adaptive learning in ELT, spells out the kind of data that can be tapped[1]:

At Knewton, we divide educational data into five types: one pertaining to student identity and onboarding, and four student activity-based data sets that have the potential to improve learning outcomes. They’re listed below in order of how difficult they are to attain:

1) Identity Data: Who are you? Are you allowed to use this application? What admin rights do you have? What district are you in? How about demographic info?

2) User Interaction Data: User interaction data includes engagement metrics, click rate, page views, bounce rate, etc. These metrics have long been the cornerstone of internet optimization for consumer web companies, which use them to improve user experience and retention. This is the easiest to collect of the data sets that affect student outcomes. Everyone who creates an online app can and should get this for themselves.

3) Inferred Content Data: How well does a piece of content “perform” across a group, or for any one subgroup, of students? What measurable student proficiency gains result when a certain type of student interacts with a certain piece of content? How well does a question actually assess what it intends to? Efficacy data on instructional materials isn’t easy to generate — it requires algorithmically normed assessment items. However it’s possible now for even small companies to “norm” small quantities of items. (Years ago, before we developed more sophisticated methods of norming items at scale, Knewton did so using Amazon’s “Mechanical Turk” service.)

4) System-Wide Data: Rosters, grades, disciplinary records, and attendance information are all examples of system-wide data. Assuming you have permission (e.g. you’re a teacher or principal), this information is easy to acquire locally for a class or school. But it isn’t very helpful at small scale because there is so little of it on a per-student basis. At very large scale it becomes more useful, and inferences that may help inform system-wide recommendations can be teased out.

5) Inferred Student Data: Exactly what concepts does a student know, at exactly what percentile of proficiency? Was an incorrect answer due to a lack of proficiency, or forgetfulness, or distraction, or a poorly worded question, or something else altogether? What is the probability that a student will pass next week’s quiz, and what can she do right this moment to increase it?

Software of this kind keeps complex personal profiles, with millions of variables per student, on as many students as necessary. The more student profiles (and therefore students) that can be compared, the more useful the data is. Big players in this field, such as Knewton, are aiming for student numbers in the tens to hundreds of millions. Once data volume of this order is achieved, the ‘analytics’, or the algorithms that convert data into ‘actionable insights’ (J. Spring, ‘Education Networks’ (New York: Routledge, 2012), p.55) become much more reliable.

---

[1] http://www.knewton.com/blog/knewton/from-jose/2013/07/18/big-data-in-education/ (last accessed 9 December 2013)