An interface for learning multi-topic user profiles from implicit feedback

Abstract

A text recommender system recommends sets of documents for individualusers on the basis of user models, which are incrementally constructedgiven feedback on previous recommendations. Users are reluctant totake the time to provide such feedback explicitly. One of the contributionsof this research is an interface design for a recommender systemwhich infers document preferences by monitoring users ' actions.A second problem for recommender systems is determining the compositionof a set of recommendations, especially when users have many interests.The interface presented provides a mechanism for users to definemultiple topics of interest and control the proportions between them.Observations from initial usability tests are encouraging---theydemonstrate the system successfully learning multi-topic user profilesusing only the implicit feedback of users ' clicking and dragand-dropactions.