User Modeling for Information Filtering Based on Implicit Feedback

This study reports the results of a pair of user studies that can provide a practical basis for designing an information filtering system that employs implicit feedback for user modeling. In information filtering systems, user modeling can be used to improve the representation of a user’s information needs. User models can be constructed by hand, or learned automatically based on feedback provided by the user about the relevance of documents that they have examined. By observing user behavior, it is possible to infer implicit feedback without requiring explicit relevance judgments. Previous studies based on Internet discussion groups (USENET news) have shown reading time to be a useful source of implicit feedback for predicting a user’s preferences. Our study extends that work by examining whether reading time is useful for predicting a user’s preferences for academic and professional journal articles and by exploring whether printing behavior can usefully augment the information that reading time provides. Two user studies were conducted in which undergraduate students examined articles and abstracts related to the telecommunications and pharmaceutical industries. The new results showed that reading time could still be used to predict the user’s assessment of relevance, although reading time for journal articles and technical abstracts are longer than has been reported for USENET news documents. Observation of printing events was found to provide additional useful evidence about relevance beyond that which could be inferred from reading time. The paper concludes with some observations on the limitations of our study, future work that is needed, and the larger implications of work on implicit feedback.