Automatically building research reading lists

All new researchers face the daunting task of familiarizing themselves with the existing body of research literature in their respective fields. Recommender algorithms could aid in preparing these lists, but most current algorithms do not understand how to rate the importance of a paper within the literature, which might limit their effectiveness in this domain. We explore several methods for augmenting exist-ing collaborative and content-based filtering algorithms with measures of the inuence of a paper within the web of cita-tions. We measure inuence using well-known algorithms, such as HITS and PageRank, for measuring a node's im-portance in a graph. Among these augmentation methods is a novel method for using importance scores to inuence collaborative filtering. We present a task-centered evalua-tion, including both an ofiine analysis and a user study, of the performance of the algorithms. Results from these stud-ies indicate that collaborative filtering outperforms content-based approaches for generating introductory reading lists.