Group items tagged

Learning analytics is the use of intelligent data, learner-produced data, and analysis models to discover information and social connections, and to predict and advise on learning

I’m interested in how learning analytics can restructure the process of teaching, learning, and administration.

LA relies on some of the concepts employed in web analysis, through tools like Google Analytics, as well as those involved in data mining (see educational data mining).

At least in the digital world, there is an evolution from scarcity to abundance in many domains. This evolution creates important new opportunities and challenges for (higher) education and strongly influences the expectations of students and, increasingly, of teachers. In the media in general and music in particular, this trend is clear. The average young person in the 70s had a collection of maybe 20 LP's, which were heard at home. The average young person now has virtually all music ever recorded at her disposal, and can listen to it anywhere and anytime, via an iPod and other devices. She can share her music with friends - legally or not. Because of this great abundance of material and its availability anytime and anywhere, it is no longer meaningful to deal with music in the traditional way. One can manually manage the music on 20 physical carriers. This approach no longer works with 3,000,000 songs. A first workaround is to provide sophisticated search, so you can create playlists of songs by title, artist, etc. Then the playlist can be played without further intervention by the listener. That is roughly the original model of iTunes. It is also roughly the model of the teacher who searches for relevant learning resources, modifies and packages them and expects the student to work through the material in a more or less controlled way.

But this approach is now passé, because there is too much overhead in searching for music and creating playlists, and because it is often not at all evident to search for music that you do not know. Indeed, users now exchange playlists as well as songs. Newer applications such as last.fm, pandora, finetune, jango and seeqpod follow a different approach: they support personalized recommendations and generate playlists themselves, on the basis of user interactions. The effect is that of a radio station which is specifically tailored to the needs and characteristics of one listener. It is interesting to note that these applications rely on very different technologies to achieve this effect: last.fm is based on "social recommending", while pandora relies on a very extensive set of metadata developed in the "music genome project".

In "social networking" applications such as facebook, this evolution is taken one step further: the user can follow what his "friends" are doing and be guided in this way to interesting material, relevant applications or even face-to-face events. Such an approach could certainly prove useful in education, where social networks can facilitate "community based learning": learners can refer one another to relevant resources in much the same way that such resources spread virally on social networking sites. Note that resources in this context include teachers or other learners, as well as applications, besides content!