Diversifying citation recommendation

Literature search is one of the most important steps of the academic research. With more than one hundred thousand papers published each year just in computer science, performing a complete literature search be-comes a herculean task. Some of the existing approaches and tools for literature search cannot compete with the characteristics of today’s literature, and they suffer from ambiguity and homonymy. Techniques based on the citation information are more robust to the mentioned issues. Following the idea, we have recently built a web service called theadvisor which provides personalized recommendations to the researchers based on their papers-of-interest. Since most recommendation methods may return redundant results, diversify-ing the results of the search process is necessary to increase the amount of information one can reach via an automized search. This paper targets the problem of result diversification in citation-based bibliographic search, assuming that the citation graph itself is the only information available, and no categories or intents are known. The contribution of this work is three-fold: We survey various random-walk-based diversifica-tion methods and enhance them with the direction awareness property to allow the users to reach either old, foundational (possibly well-cited and well-known) research papers or recent (most likely less-known) ones. Next, we propose a set of novel algorithms based on vertex selection and query refinement. A set of experi-ments with various evaluation criteria shows that the proposed γ-RLM algorithm performs better than th