Notes about Learning Analytics part3

Perhaps it is normal behavior to be very enthusiastic during the conference and then slowly forget that. It is the same if you have participated f2f or online. Time will tell what remains valuable in my mind. But I took a screencast during the LAK conference, it is a nice memory for me.

Rita Kop is speaking about the PLENK research and there are two participants in the chat room (it is a fake, Viplav wasn’t there at this moment, he visited on the first day but I could take the photo because the chat wasn’t used after that). Rita in Canada, Viplav in India and me in Finland.



In this post I continue only one topic more.

Erik Duval spoke in the LAK conference about the Quantified Self. He was worried about the situation: It is possible to follow so much about our living that it is dangerous. How to use all data for benefit of people, not to spy or control. It is an ethical question really. Awareness about one’s learning is the key. All people are not conscious about their doings, and misusing data could be very easy.

I listened to some videos on Vimeo from Quantified Self Amsterdam, Glenn Wolters and Jeroen Bos presenting a project Lifelapse. They offer tools for knowing your own mind and body, timelapse your life anywhere. They used a concept digital subconscious for extending human mind. I feel confused, really! Where are we going with all this data?

Learning Analytics about PLENK and me

I continue my pondering about learning analytics and use myself as a case in PLENK course. Rita Kop was one of the facilitators and she had a presentation in the first LA conference some days ago. She has blogged about the conference twice.

First I gather things that I consider most interesting in Rita’s and Helene’s slides. The boldings are mine.

  • Many different people as participants – professors and researchers, designers, teachers. Got demographics, 55 and older group are a majority of participants. Spread across the globe.
  • What did they do? Used a variety of tools – high number of blog posts, even higher number of Twitter posts, increases steadily over the ten weeks. Aggregated posts via the tag. Elluminate, Moodle were steady but low throughout. Only 40-60 individuals participated actively on a regular basis and produced blog posts.
  • Had to rethink research methods, the environment much bigger. Complexity. Many issues. For instance, ethical issues in collecting big data. Can’t just use data that people have given for another purpose.
  • Thematic analysis – learning is the central concept. Agency, the I/me ownership of the discussions were sub-concepts.
  • Did qualitative and quantitative methods. Virtual ethnography, focus groups, surveys, data mining. Very crude analysis so far, thematic analysis, learner analytics and visualization, stats on surveys.
  • Found analytics helpful; visualization did clarify things didn’t notice from traditional qualitative methods. But still need those to capture depth. Ethics implications are there. Linking data could be used to enhance learning.

There was discussion after the presentation and it was a little weird to listen to it because I was one of them, the voluntary participants in PLENK. Somebody asked if “facilitator said one thing, had a huge effect?  Did you look at types of post that really got people worked up?and here come the answer:

Rita: The posts that get people going the most are controversial statements. Have to think how to word it to generate participation. Had huge number of participants, once ball is rolling people spark off each other. Twitter interesting in linking blog posts back to discussion forums. Twitter has been an important part in that.

Question: Big challenge, have an arbitrary number of systems – an SNA for Moodle, Flickr, Twitter – how do you merge those? Huge challenge. Rita: Definitely. If you want analytics to work on a multi-platform, have to connect them ..

Rita: Had discussion after the course. Large number participated, but not by producing material. Dropping out? .. want to know why people dropped out. The pattern on the internet of participation? Also, about 54% said they were self-directed learners and didn’t need to communicate. Also a lot of novices who said they needed the time before they would participate and produce things.

Now I continue with my experiences. I am one of those 55+ self-directed learners and I made own summaries after the course. I was glad about the link to this blog (in Rita’s presentation), Google Analytics is in use and sharing it with others is my habit. I also summarized Moodle activity by checking the amount of writings (I could see it only from profiles, it was rough measure).

Ethical questions arose when I blogged about these results. What can I say aloud, I don’t want to assess my co-learners in public. I dared to say that Chris Jobling was our main reflector, Susans (2) were perhaps emotional supporters and Ken had critical questions. It was nice to get comments, some were pleased to my blog post.  I remember that I had other ideas, for instance the place of technological skills (Chris, Susan etc) on forums. I analysed publicly only my participation (only greeted friends and answered to questions of Google map, nothing important).

What is the amount of technical questions and problems, new tools – is it about 80% of all discussions? I was disappointed about the interpretation that PLE means only technological environment of learners. But if this is basic agreement, so it is no wonder that technology rules. Open courses are for nerds, mainly? – In the slides learning, agency and ownership were said to be the themes most in use. Learning + Technology?

I had an idea to follow my connections and learning during the course, but soon I understood that I can report my thinking only partially. I wanted to connect to some people and not to some others. Jenny’s and Matthias’s paper about eResonance interested me, but I could not proceed very much. I blogged something about my experiences, how I felt tired … I have decided 19.11.2010 to change the name of this blog and stop to participate in open courses if they have only general themes (like PLENK). But I continued to analyse learning and still do.

Just now I have many questions from Mohsen Saadatmand waiting. Excellent questions, it takes many days to answer and I am sure that I learn a lot while reflecting my answers. And I wait with great interest more results from Rita and Helene. This was only beginning.

Learning Analytics – 1st conference

I had a pleasure to listen to Ustream of LAK11 conference. It was cold weather there but I sat in my warm room at home. I recognized that I have always (online teacher ten years) been interested in the analytical possibilities of the learning platforms which I used in facilitating learning. I used to offer group reflections and feedback to my students all the time. And now was first conference about these topics. Doug Clow blogged almost all, never seen so perfect conference blog, thanks to him.

David Wiley grasped key questions, I appreciate it. Are we “Letting the data tail wag the theory dog” ?

  • Interpretation != science?
  • Confusion of science with positivism: Social scientists have “physics envy”, quantity > quality
  • Educational measurement: what does he/she know? Research that is mediated by observation – can’t crack open the  learner’s head … People engage in behaviours, and we take those behaviours.
  • Observable behaviour online is expressed in restricted vocabulary to key presses and mouse clicks.
  • Westerman’s argument: Quantitative inquiry is interpretive.
  • Can we call it success, if we can predict, but we don’t understand why?
  • If not positivism… then what? Hermeneutics – meaning and interpretation
  • Problems with metaphor – information processing model – only works when the brain is operating like a computer. Breaks down when creativity is involved
  • Reductionism – “nothing more to be said when neurophysiology has had it’s say”

Behaviour in context, social practice:  How do we observe behaviour in online environments? We need

  • Structural equation modeling
  • Multilevel data structures
  • Continuous, longitudinal measures
  • Tasks nested within practice

Using Learning analytics is an ethical activity .

David said what I wanted to hear. After his presentation we heard many reports which tried to proceed in describing network (mathematical) models and many quantitative measurements. I could not follow all because I don’t know enough .. know only psychological and educational sciences. Modeling behavior is collaborative work, very challenging. Some examples here:

Xavier Ochoa is a Principal Professor at the Faculty of Electrical and Computer Engineering in Guayaquil Ecuador. Learnometrics was the theme and he pondered how to proceed from empirical rugularities to mathematical models. How to understand influence, produce useful metrics? Learning repositories are not working because growth is linear, not exponential like youtube, why so?. Slides here. Data mining <analytics < research, what are the chains from one to other? Similarities and differences between LA and educational measurement, image.

Dan Suthers – Unified Framework for Multi-Level Analysis of Distributed Learning. Slides here. Interesting concepts and questions: Networked individualism? Ties, sequential analysis of interactions? How people live through processes to insight?

Second day of LAK11 conference was more practical. It was women’s day, first was men’s 🙂 . But of course there was a man as a key lecturer: Erik Duval, Attention please! Attention metadata and interaction. Program says:

Attention metadata capture how people interact with resources and with one another. We can make use of the patterns in attention metadata to help learners and teachers cope with the abundance of learning resources through recommendation techniques. By visualizing the patterns, we can make teachers and learners more aware of what they do. An important concern is openness, so that we can detect patterns across the boundaries of technical and organizational systems and ensure data portability that prevents system lock-in.

Erik Duval is a professor of computer science at the Katholieke Universiteit Leuven, Belgium. His research focuses on management of and access to data and content. Typical applications come from the fields of technology- enhanced learning, music information retrieval, and “Science2.0.” It possible to follow so much about our living that it is dangerous. How to work for benefit of people, not to spy or control. It is an ethical question really. Awareness about one’s learning is the key. Slides here.

Caroline Haythornthwaite from University of British Columbia, Vancouver. Her theme was Learning networks, crowds and communities. A copy of the program:

Who we learn from, where and when is dramatically affected by the reach of the Internet. From learning for formal education to learning for pleasure, we now look to the web early and often for our data and knowledge needs, but also for places and spaces where we can collaborate, contribute to, and create learning and knowledge communities. This talk explores the emerging landscape of online learning with attention to the structure and dynamics of online learning networks, crowds and communities. With reference to social network informed studies of learning, the talk explores the different ways learning emerges from social interaction, how structures and motivators differ across ‘lightweight’ (crowd-based) and ‘heavyweight’ (community-based) peer productions, and where an analytics perspective can be used to follow, support or enhance learning outcomes.

Many research projects were presented about learning in social contexts. I am too tired now to continue, have already surpassed myself  and need a break. It was fine to hear from many research projects which are going on in Europe and other continents. If you are interested in learner analytics, please read the program. No sense in copying more here 😉

I will write about the presentation of Rita Kop and Helene Fournier in another post. It is the only one I know as a student in Plenk2010 course.