Recommender

Recommendations for your course

How do you find appropriate content in a large repository? The same way that you find things in an online bookstore.

Online bookstores can do this, since they know what other customers put into the same shopping basket, and they know what you bought in the past. LON-CAPA knows the same things: it knows what other instructors put into the same chapters and the same assignments, and it knows what you selected in the past.

Quality assurance

In addition, for interactive resources, LON-CAPA can give quality and effectiveness measures, since the close integration of repository and deployment allows for efficient usage tracking, data mining, and analytics.

It’s possible!

Does this work? Analysis of selection data from the LON-CAPA repository yielded some 2.8 million association rules, which lead to useful recommendations. Analytics of the 200,000 problems in the pool are based on 138,320,000 student transactions. An end-to-end solution allows for data to flow back.

Repository

A shared repository

All content is held in a shared repository, just like in an online music store, from all different sources and at all different levels of granularity.

The repository maintains a permanent link for all content materials, so you can rely on selected content to be available. It provides versioning, so previous versions of content can be retrieved and changes tracked, and it provides replication to avoid bottleneck situations.

Finally, it provides cataloging data (“metadata”) for the content, both static (title, keyword, subject, taxonomy, …) and dynamic (usage, context, accesses, difficulty, …) – data that will feed into the recommender.

It’s possible!

Will this actually work? We know it does, since it does in LON-CAPA, where over the years over 450,000 pieces of content have been contributed to a common repository. This content is going to form the base of LON-CAPA.