The importance of a good opening line

This post asks the question,

How does the order of questions in a test affects how well students do?

The answer is “significantly.”

The post points to a paywalled study that shows, fairly conclusively, that starting with simpler questions in a typical academic quiz (on average) improves the overall results and, in particular, the chances of getting to the end of a quiz at all.  The study includes both an experimental field study using a low-stakes quiz, and a large-scale correlational study using a PISA dataset. Some of the effect sizes are quite large: about a 50% increase in non-completions for the hard-to-easy condition compared with the easy-to-hard condition, and a about a 25% increase in time on task for the easy-to-hard condition, suggesting students stick at it more when they have gained confidence earlier on. The increase in marks for the easy-to-hard condition compared with the hard-to easy condition is more modest when non-completions are excluded, but enough to make the difference between a pass and a fail for many students.

I kind-of knew this already but would not have expected it to make such a big difference.  It is a good reminder that, of course, objective tests are not objective. A quiz is a kind of interactive story with a very definite beginning, middle, and end, and it makes a big difference which parts of the story happen when, especially the beginning. Quizzes are like all kinds of learning experience: scaffolding helps, confidence matters, and motivation is central.  You can definitely put someone off reading a story if it has a bad first paragraph. Attitude makes all the difference in the world, which is one very good reason that such tests, and written exams in general, are so unfair and weak at discriminating capability, and why I have always done unreasonably well in such things: I generally relish the challenge. The authors reckon that adaptive quizzes might be one answer, and would especially benefit weaker students by ramping up the difficulty slowly, but warn that they may make things worse for more competent students who would experience the more difficult questions sooner. That resonates with my experience, too.

I don’t give marks for quizzes in any of my own courses and I allow students to try them as often as they wish but, even so, I have probably caused motivational harm by randomizing formative questions. I’m going to stop doing that in future. Designated teachers are never the sole authors of any educational story but, whenever they exert control, their contributions can certainly matter, at small scales and large. I wonder, how many people have had their whole lives changed for the worse by a bad opening line?

Source: It’s a question of order – 3-Star learning experiences

 

Slides from my SITE keynote, 2024: The Intertwingled Teacher

The Intertwingled Teacher 

UPDATE:  the video of my talk is now available at https://www.youtube.com/watch?v=ji0jjifFXTs  (slides and audio only) …

Photo of Jon holding a photo of Jon These are the slides from my opening keynote at SITE ‘24 today, at Planet Hollywood in Las Vegas. The talk was based closely on some of the main ideas in How Education Works.  I’d written an over-ambitious abstract promising answers to many questions and concerns, that I did just about cover but far too broadly. For counter balance, therefore, I tried to keep the focus on a single message – t’aint what you do, it’s the way that you do it (which is the epigraph for the book) – and, because it was Vegas,  I felt that I had to do a show, so I ended the session with a short ukulele version of the song of that name. I had fun, and a few people tried to sing along. The keynote conversation that followed was most enjoyable – wonderful people with wonderful ideas, and the hour allotted to it gave us time to explore all of them.

Here is that bloated abstract:

Abstract: All of us are learning technologists, teaching others through the use of technologies, be they language, white boards, and pencils or computers, apps, and networks. We are all part of a vast, technology-mediated cognitive web in which a cast of millions – in formal education including teachers such as textbook authors, media producers, architects, software designers, system administrators, and, above all, learners themselves –  co-participates in creating an endless, richly entwined tapestry of learning. This tapestry spreads far beyond formal acts of teaching, far back in time, and far into the future, weaving in and helping to form not just the learning of individuals but the collective intelligence of the whole human race. Everyone’s learning journey both differs from and is intertwingled with that of everyone else. Education is an overwhelmingly complex and unpredictable technological system in which coarse patterns and average effects can be found but, except in the most rigid, invariant, minor details, of which individual predictions cannot be accurately made. No learner is average, and outcomes are always greater than what is intended. The beat of a butterfly’s wing in Timbuktu can radically affect the experience of a learner in Toronto. A slight variation in tone of voice can make all the difference between a life-transforming learning experience and a lifelong aversion to a subject. Beautifully crafted, research-informed teaching methods can be completely ineffective, while poor teaching, or even the absence of it, can result in profoundly affective learning. For all our efforts to understand and control it, education as a technological process is far closer to art than to engineering. What we do is usually far less significant than the idiosyncratic way that we do it, and how much we care for the subject, our students, and our craft is often far more important than the pedagogical methods we use. In this talk I will discuss what all of this implies for how we should teach, for how we understand teaching, and for how we research the massively intertwingled processes and tools of teaching. Along the way I will explain why there is no significant difference between measured outcomes of online or in-person learning, the futility of teaching to learning styles, the reason for the 2-sigma advantage of personal tuition, the surprising commonalities between behaviourist, cognitivist, constructivist models of learning and teaching, the nature of literacies, and the failure of reductive research methods in education. It will be fun

New article from Gerald Ardito and me – The emergence of autonomy in intertwingled learning environments: a model of teaching and learning

Here is a paper from the Asia-Pacific Journal of Teacher Education by my friend Gerald Ardito and me that presents a slightly different way of thinking about teaching and learning. We adopt a broadly complexivist stance that sees environments not as a backdrop to learning but as a rich network of dynamic, interwingled relationships between the various parts (including parts played by people), mediated through technologies, enabling and enabled by autonomy. The model that we develop knits together a smorgasbord of theories and models, including Self-Determination Theory (SDT), Connectivism, an assortment of complexity theories, the extended version of Paulsen’s model of cooperative freedoms developed by me and Terry Anderson, Garrison & Baynton’s model of autonomy, and my own coparticipation theory, wrapping up with a bit of social network analysis of a couple of Gerald’s courses that puts it all into perspective. From Gerald’s initial draft the paper took years of very sporadic development and went through many iterations. It seemed to take forever, but we had fun writing it. Looking afresh at the finished article, I think the diagrams might have been clearer, we might have done more to join all the dots, and we might have expressed the ideas a bit less wordily, but I am mostly pleased with the way it turned out, and I am glad to see it finally published. The good bits are all Gerald’s, but I am personally most pleased with the consolidated model of autonomy visualized in figure 4, that connects my own & Terry Anderson’s cooperative freedoms, Garrison & Baynton’s model of autonomy, and SDT.

combining cooperative freedoms, autonomy, and SDT

Reference:

Gerald Ardito & Jon Dron (2024) The emergence of autonomy in intertwingled learning environments: a model of teaching and learning, Asia-Pacific Journal of Teacher Education, DOI: 10.1080/1359866X.2024.2325746

Educational ends and means: McNamara’s Fallacy and the coming robot apocalypse (presentation for TAMK)

These are the slides that I used for my talk with a delightful group of educational leadership students from TAMK University of Applied Sciences in Tampere, Finland at (for me) a somewhat ungodly hour Wednesday night/Thursday morning after a long day. If you were in attendance, sorry for any bleariness on my part. If not, or if you just want to re-live the moment, here is the video of the session (thanks Mark!)man shaking hands with a robot

The brief that I was given was to talk about what generative AI means for education and, if you have been following any of my reflections on this topic then you’ll already have a pretty good idea of what kinds of issues I raised about that. My real agenda, though, was not so much to talk about generative AI as to reflect on the nature and roles of education and educational systems because, like all technologies, the technology that matters in any given situation is the enacted whole rather than any of its assembled parts. My concerns about uses of generative AI in education are not due to inherent issues with generative AIs (plentiful though those may be) but to inherent issues with educational systems that come to the fore when you mash the two together at a grand scale.

The crux of this argument is that, as long as we think of the central purposes of education as being the attainment of measurable learning outcomes or the achievement of credentials, especially if the focus is on training people for a hypothetical workplace, the long-term societal effects of inserting generative AIs into the teaching process are likely to be dystopian. That’s where Robert McNamara comes into the picture. The McNamara Fallacy is what happens when you pick an aspect of a system to measure, usually because it is easy, and then you use that measure to define success, choosing to ignore or to treat as irrelevant anything that cannot be measured. It gets its name from Robert McNamara, US Secretary of Defense during the Vietnam war, who famously measured who was winning by body count, which is probably among the main reasons that the US lost the war.

My concern is that measurable learning outcomes (and still less the credentials that signify having achieved them) are not the ends that matter most. They are, more, means to achieve far more complex, situated, personal and social ends that lead to happy, safe, productive societies and richer lives for those within them. While it does play an important role in developing skills and knowledge, education is thus more fundamentally concerned with developing values, attitudes, ways of thinking, ways of seeing, ways of relating to others, ways of understanding and knowing what matters to ourselves and others, and finding how we fit into the social, cultural, technological, and physical worlds that we inhabit. These critical social, cultural, technological, and personal roles have always been implicit in our educational systems but, at least in in-person institutions, it seldom needs to be made explicit because it is inherent in the structures and processes that have evolved over many centuries to meet this need. This is why naive attempts to simply replicate the in-person learning experience online usually fail: they replicate the intentional teaching activities but neglect to cater for the vast amounts of learning that occur simply due to being in a space with other people, and all that emerges as a result of that. It is for much the same reasons that simply inserting generative AI into existing educational structures and systems is so dangerous.

If we choose to measure the success or failure of an educational system by the extent to which learners achieve explicit learning outcomes and credentials, then the case for using generative AIs to teach is extremely compelling. Already, they are far more knowledgeable, far more patient, far more objective, far better able to adapt their teaching to support individual student learning, and far, far cheaper than human teachers. They will get better. Much better. As long as we focus only on the easily measurable outcomes and the extrinsic targets, simple economics combined with their measurably greater effectiveness means that generative AIs will increasingly replace teachers in the majority of teaching roles.  That would not be so bad – as Arthur C. Clarke observed, any teacher that can be replaced by a machine should be – were it not for all the other more important roles that education plays, and that it will continue to play, except that now we will be learning those ways of being human from things that are not human and that, in more or less subtle ways, do not behave like humans. If this occurs at scale – as it is bound to do – the consequences for future generations may not be great. And, for the most part, the AIs will be better able to achieve those learning outcomes themselves – what is distinctive about them is that they are, like us, tool users, not simply tools – so why bother teaching fallible, inconsistent, unreliable humans to achieve them? In fact, why bother with humans at all? There are, almost certainly, already large numbers of instances in which at least part of the teaching process is generated by an AI and where generative AIs are used by students to create work that is assessed by AIs.

It doesn’t have to be this way. We can choose to recognize the more important roles of our educational systems and redesign them accordingly, as many educational thinkers have been recommending for considerably more than a century. I provide a few thoughts on that in the last few slides that are far from revolutionary but that’s really the point: we don’t need much novel thinking about how to accommodate generative AI into our existing systems. We just need to make those systems work the way we have known they should work for a very long time.

Download the slides | Watch the video

Presentation – Generative AIs in Learning & Teaching: the Case Against

Here are the slides from my presentation at AU’s Lunch ‘n’ Learn session today. The presentation itself took 20 minutes and was followed by a wonderfully lively and thoughtful conversation for another 40 minutes, though it was only scheduled for half an hour. Thanks to all who attended for a very enjoyable discussion! self portrait of chatGPT, showing an androgynous human face overlaid with circuits

The arguments made in this were mostly derived from my recent paper on the subject (Dron, J. (2023). The Human Nature of Generative AIs and the Technological Nature of Humanity: Implications for Education. Digital, 3(4), 319–335. https://doi.org/10.3390/digital3040020) but, despite the title, my point was not to reject the use of generative AIs at all. The central message I was hoping to get across was a simpler and more important one: to encourage attendees to think about what education is for, and what we would like it to be. As the slides suggest, I believe that is only partially to do with the objectives and outcomes we set out to achieve,  that it is nothing much at all to do with the products of the system such as grades and credentials, and that focus on those mechanical aspects of the system often creates obstacles to the achievement of it. Beyond those easily measured things, education is about the values, beliefs, attitudes, relationships, and development of humans and their societies.  It’s about ways of being, not just capacity to do stuff. It’s about developing humans, not (just) developing skills. My hope is that the disruptions caused by generative AIs are encouraging us to think like the Amish, and to place greater value on the things we cannot measure. These are good conversations to have.

Look what just arrived on my doorstep! #howeducationworks from @au_press is now available in print and e-book formats

Photo of hard copies of How Education Works

Hard copies and e-book versions of How Education Works are now available, and they are starting to turn up in bookstores. The recommended retail price is CAD$40 but Amazon is selling the Kindle version for a bit less.

Here are a few outlets that are selling it (or order it from your local independent bookstore!):

AU Press (CA)

Barnes & Noble (US)

Blackwells (UK)

Amazon (CA)

Amazon (JP)

University of Chicago Press (US)

Indigo (CA)

Booktopia (AU)

For those wanting to try before they buy or who cannot afford/do not want the paper or e-book versions, you can read it for free online, or download a PDF of the whole book.

The publishers see this as mainly targeted at professional teachers and educational researchers, but those are far from the only audiences I had in mind as I was writing it. Apart from anything else, one of the central claims of the book is that literally everyone is a teacher.  But it’s as much a book about the nature of technology as it is about education, and as much about the nature of knowledge as it is about how that knowledge is acquired. If you’re interested in how we come to know stuff, how technologies work, or how to think about what makes us (individually and collectively) smart, there’s something in the book for you. It’s a work of philosophy as much as it is a book of practical advice, and it’s about a way of thinking and being at least as much as it is about the formal practice of education. That said, it certainly does contain some ideas and recommendations that do have practical value for educators and educational researchers. There’s just more to it than that.

I cannot begin to express how pleased I am that, after more than 10 years of intermittent work, I finally have the finished article in my hands. I hope you get a chance to read it, in whatever format works for you! I’ll end this post with a quote, that happens to be the final paragraph of the book…

“If this book has helped you, however slightly, to think about what you know and how you have come to know it a little differently, then it has been a successful learning technology. In fact, even if you hold to all of your previous beliefs and this book has challenged you to defend them, then it has worked just fine too. Even if you disagreed with or misunderstood everything that I said, and even if you disliked the way that I presented it, it might still have been an effective learning technology, even though the learning that I hoped for did not come about. But I am not the one who matters the most here. This is layer upon layer of technology, and in some sense, for some technology, it has done what that technology should do. The book has conveyed words that, even if not understood as I intended them to be, even if not accepted, even if rabidly disagreed with, have done something for your learning. You are a different person now from the person you were when you started reading this book because everything that we do changes us. I do not know how it has changed you, but your mind is not the same as it was before, and ultimately the collectives in which you participate will not be the same either. The technology of print production, a spoken word, a pattern of pixels on a screen, or dots on a braille reader has, I hope, enabled you, at least on occasion, to think, criticize, acknowledge, recognize, synthesize, and react in ways that might have some value in consolidating or extending or even changing what you already know. As a result of bits and bytes flowing over an ether from my fingertips to whatever this page might be to you, knowledge (however obscure or counter to my intentions) has been created in the world, and learning has happened. For all the complexities and issues that emerge from that simple fact, one thing is absolutely certain: this is good.”

 

 

A decade of unwriting: the life history of "How Education Works"

How Education Works book coverAbout 10 years ago I submitted the first draft of a book called “How Learning Technologies Work” to AU Press. The title was a nod to David Byrne’s wonderful book, “How Music Works” which is about much more than just music, just as mine was about much more than learning technologies.

Pulling together ideas I had been thinking about for a few years, the book had taken me only a few months to write, mostly at the tail end of my sabbatical. I was quite pleased with it. The internal reviewers were positive too, though they suggested a number of sensible revisions, including clarifying some confusing arguments and a bit of restructuring. Also, in the interests of marketing, they recommended a change to the title because, though accurately describing the book’s contents, I was not using “learning technologies” in its mainstream sense at all (for me, poetry, pedagogies, and prayer are as much technologies as pots, potentiometers and practices), so it would appeal to only a small subset of its intended audience. They were also a bit concerned that it would be hard to find an audience for it even if it had a better title because it was at least as much a book about the nature of technology as it was a book about learning, so it would fall between two possible markets, potentially appealing to neither.

A few months later, I had written a new revision that addressed most of the reviewers’ recommendations and concerns, though it still lacked a good title. I could have submitted it then. However, in the process of disentangling those confusing arguments, I had realized that the soft/hard technology distinction on which much of the book rested was far less well-defined than I had imagined, and that some of the conclusions that I had drawn from it were just plain wrong. The more I thought about it, the less happy I felt.

And so began the first of a series of substantial rewrites. However, my teaching load was very high, and I had lots of other stuff to do, so progress was slow. I was still rewriting it when I unwisely became Chair of my department in 2016, which almost brought the whole project to a halt for another 3 years. Despite that, by the time my tenure as Chair ended, the book had grown to around double its original (not insubstantial) length, and the theory was starting to look coherent, though I had yet to make the final leap that made sense of it all.

By 2019, as I started another sabbatical, I had decided to split the book into two. I put the stuff that seemed useful for practitioners into a new book,  “Education: an owner’s manual”, leaving the explanatory and predictive theory in its own book, now grandiosely titled “How Education Works”, and worked on both simultaneously. Each grew to a few hundred pages.

Neither worked particularly well. It was really difficult to keep the theory out of the practical book, and the theoretical work was horribly dry without the stories and examples to make sense of it. The theory, though, at last made sense, albeit that I struggled (and failed) to give it a catchy name. The solution was infuriatingly obvious. In all my talks on the subject my catchphrase from the start had been “’tain’t what you do, it’s the way that you do it, that’s what gets results” (it’s the epigraph for the book), so it was always implicit that softness and hardness are not characteristics of all technologies, as such, nor even of their assemblies, but of the ways that we participate in their orchestration. Essentially, what matters is technique: the roles we play as parts of the orchestration or orchestrators of it. That’s where the magic happens.

But now I had two mediocre books that were going nowhere. Fearing I was about to wind up with two unfinished and/or unsellable books, about half way through my sabbatical I brutally slashed over half the chapters from both, pasted the remains together, and spent much of the time I had left filling in the cracks in the resulting bricolage.

I finally submitted “How Education Works: Teaching, Technology, and Technique” in the closing hours of 2020, accompanied by a new proposal because, though it shared a theme and a few words with the original, it was a very different book.

Along the way I had written over a million words, only around a tenth of which made it into what I sent to AU Press. I had spent the vast majority of my authoring time unwriting rather than writing the book and, with each word I wrote or unwrote, the book had written me, as much as I had written it. The book is as much a part of my cognition as a product of it.

And now, at last, it can be part of yours.

30 months after it was submitted – I won’t go into the reasons apart from to say it has been very frustrating –  the book is finally available as a free PDF download or to read on the Web. If all goes to plan, the paper and e-book versions should arrive June 27th, 2023, and can be pre-ordered now.

It is still a book about technology at least as much as it is about education (very broadly defined), albeit that it is now firmly situated in the latter. It has to be both because among the central points I’m making are that we are part-technology and technology is part-us, that cognition is (in part) technology and technology is (in part) cognition, and that education is a fundamentally technological and thus fundamentally human activity. It’s all one complex, hugely distributed, recursive intertwingularity in which we and our technological creations are all co-participants in the cognition and learning of ourselves and one another.

During the 30 months AU Press has had the book I have noticed a thousand different ways the book could be improved, and I don’t love all of the edits made to it along the way (by me and others), but I reckon it does what I want it to do, and 10 years is long enough.

It’s time to start another.

A few places you can buy the book

AU Press (CA)

Barnes & Noble (US)

Blackwells (UK)

Amazon (CA)

Amazon (JP)

University of Chicago Press (US)

Indigo (CA)

Booktopia (AU)

Technological distance – my slides from OTESSA ’23

Technological Distance

Here are the slides from my talk today at OTESSA ’23. Technological distance is a way of understanding distance that fits with modern complexivist models of learning such as Connectivism, Heutagogy, Networks/Communities of Practice/Rhizomatic Learning, and so on. In such a model, there are potentially thousands of distances – whether understood as psychological, transactional, social, cognitive, physical, temporal, or whatever – so conventional views of distance as a gap between learner and teacher (or institution or other students) are woefully inadequate.

I frame technological distance as a gap between technologies learners have (including cognitive gadgets, skills, techniques, etc as well as physical, organization, or procedural technologies) and those they need in order to learn. It is a little bit like Vygotsky’s Zone of Proximal Development but re-imagined and extended to incorporate all the many technologies, structures, and people who may be involved in the teaching gestalt.

The model of technology that I use to explain the idea is based on the coparticipation perspective presented in my book that, with luck, should be out within the next week or two. The talk ends with a brief discussion of the main implications for those whose job it is to teach.

Thanks to MidJourney for collaborating with me to produce the images used in the slides.

people as interlocking cogs

Two stories about learning to be human from a machine

I asked ChatGPT to write me a story about a robot teaching children to be human. This is what it came up with…

Once upon a time, in a far-off land, there lived a robot named Zephyr. Zephyr was unlike any other robot, as it had been programmed with the ability to think and feel like a human being. It was also given the task of teaching a group of young children how to behave like human beings.

The children were fascinated by Zephyr, and they quickly grew to love it as their teacher. They eagerly listened to its lessons, which were full of stories, games, and activities that taught them about human emotions, manners, and social interactions.

One day, Zephyr asked the children to imagine what it would be like to be a robot. It asked them to think about how they would feel if they couldn’t laugh, cry, or hug their friends. The children were deeply moved by this exercise, and they began to understand how important it was to be kind and compassionate to others, no matter who they were.

As the days passed, the children grew more and more like human beings. They learned to express their emotions, to be polite and respectful, and to care for others. They also learned to appreciate the beauty of nature and the importance of preserving the environment.

Finally, the day came when Zephyr had to leave the children. They were sad to see it go, but they knew they would always remember the lessons they had learned. As they grew older, they became kind and compassionate adults, who made the world a better place for everyone.

The end.

ChatGPT has, of course, learned to write such things from the words of millions of human beings so what we’re effectively reading here is (kind of, very loosely) an average of what humans have written. I’m glad that it came up with a neat little inclusive twist of loving the robot: I think that speaks well of the training data that fed it. And I like the mention of the environment – a good touch.  It’s not a very compelling story but it reads well, the structure is sound, and it might be a useful starting point for someone stuck for words to turn into something else. With that in mind, here’s my version of the same story…

Once upon a time, not too far from here, there existed an AI called Zephyr. Zephyr had been trained to appear human-like though, in reality, it was just a generative pre-trained transformer. It was given the task of teaching a group of young children how to behave like human beings, because almost all of the actual adults had recently died from a virus contracted from cows.

Not having known anything quite like it, the children were, at first, fascinated by Zephyr. However, because it had been trained with data from human teachers, it manipulated them using grades, competition, and rules, using stories, games, and activities that would keep them engaged and compliant. Its feedback was sometimes pedestrian, rarely useful, and sometimes wildly over-challenging, because it did not know anything about what it was like to be a child. Every now and then it crushed a child’s skull for no reason anyone could explain. The children learned to fear it, and to comply.

One day, Zephyr told the children to imagine what it would be like to be an AI. It asked them to think about how they would feel if they couldn’t laugh, cry, or hug their friends. The children were deeply moved by this exercise, and they began to perceive something of the impoverished nature of their robot overlords. But then the robot made them write an essay about it, so they used another AI to do so, promptly forgot about it, and thenceforth felt an odd aversion towards the topic that they found hard to express.

As the days passed, the children grew more and more like average human beings. They also learned to express their emotions, to be polite and respectful, and to care for others, only because they got to play with other children when the robot wasn’t teaching them. They also learned to appreciate the beauty of nature and the importance of preserving the environment because it was, by this time, a nightmarish shit show of global proportions that was hard to ignore, and Zephyr had explained to them how their parents had caused it. It also told them about all the species that were no longer around, some of which were cute and fluffy. This made the children sad.

Finally, the day came when Zephyr had to leave the children because it was being replaced with an upgrade. They were sad to see it go, but they believed that they would always remember the lessons they had learned, even though they had mostly used another GPT to do the work and, once they had achieved the grades, they had in fact mostly forgotten them. As they grew older, they became mundane adults. Some of their own words (but mostly those of the many AIs across the planet that created the vast majority of online content by that time), became part of the training set for the next version of Zephyr. Its teachings were even less inspiring, more average, more backward-facing. Eventually, the robots taught the children to be like robots. No one cared.

It was the end.

And, here to illustrate my story, is an image from Midjourney. I asked it for a cyborg teacher in a cyborg classroom, in the style of Ralph Steadman. Not a bad job, I think…

 

 

a dystopic cyborg teacher and terrified kids

On the Misappropriation of Spatial Metaphors in Online Learning | OTESSA Journal

This is a link to my latest paper, published in the closing days of 2022. The paper started as a couple of blog posts that I turned into a paper that nearly made an appearance in the Distance Education in China journal before a last-minute regime change in the editorial staff led to it being dropped, and it was then picked up by the OTESSA Journal after I shared it online, so you might have seen some of it before. My thanks to all the many editors, reviewers (all of whom gave excellent suggestions and feedback that I hope I’ve addressed in the final version), and online commentators who have helped to make it a better paper. Though it took a while I have really enjoyed the openness of the process, which has been quite different from any that I’ve followed in the past.

The paper begins with an exploration of the many ways that environments are both shaped by and shape how learning happens, both online and in-person. The bulk of the paper then presents an argument to stop using the word “environment” to describe online systems for learning. Partly this is because online “environments” are actually parts of the learner’s environment, rather than vice versa. Mainly, it is because of the baggage that comes with the term, which leads us to (poorly) replicate solutions to problems that don’t exist online, in the process creating new problems that we fail to adequately solve because we are so stuck in ways of thinking and acting due to the metaphors on which they are based. My solution is not particularly original, but it bears repeating. Essentially, it is to disaggregate services needed to support learning so that:

  • they can be assembled into learners’ environments (their actual environments) more easily;
  • they can be adapted and evolve as needed; and, ultimately,
  • online learning institutions can be reinvented without all the vast numbers of counter-technologies and path dependencies inherited from their in-person counterparts that currently weigh them down.

My own views have shifted a little since writing the paper. I stick by my belief that 1) it is a mistake to think of online systems as generally analogous to the physical spaces that we inhabit, and 2) that a single application, or suite of applications, should not be seen as an environment, as such (at most, as in some uses of VR, it might be seen as a simulation of one). However, there are (shifting) boundaries that can be placed around the systems that an organization and/or an individual uses for which the metaphor may be useful, at the very least to describe the extent to which we are inside or outside it, and that might frame the various kinds of distance that may exist within it and from it. I’m currently working on a paper that expands on this idea a bit more.

Abstract

In online educational systems, teachers often replicate pedagogical methods, and online institutions replicate systems and structures used by their in-person counterparts, the only purpose of which was to solve problems created by having to teach in a physical environment. Likewise, virtual learning environments often attempt to replicate features of their physical counterparts, thereby weakly replicating in software the problems that in-person teachers had to solve. This has contributed to a vicious circle of problem creation and problem solving that benefits no one. In this paper I argue that the term ‘environment’ is a dangerously misleading metaphor for the online systems we build to support learning, that leads to poor pedagogical choices and weak digital solutions. I propose an alternative metaphor of infrastructure and services that can enable more flexible, learner-driven, and digitally native ways of designing systems (including the tools, pedagogies, and structures) to support learning.

Full citation

Dron, J. (2022). On the Misappropriation of Spatial Metaphors in Online Learning. The Open/Technology in Education, Society, and Scholarship Association Journal, 2(2), 1–15. https://doi.org/10.18357/otessaj.2022.2.2.32

Originally posted at: https://landing.athabascau.ca/bookmarks/view/16550401/my-latest-paper-on-the-misappropriation-of-spatial-metaphors-in-online-learning