TechLens+: A Hybrid Approach to Recommending Research Papers

• Roberto Torres UFRGS / University of Minnesota
• Mara Abel UFRGS
• John Riedl University of Minnesota

Resumo

In this paper, we present and test hybrid recommender algorithms that combine Collaborative Filtering and Content-based Filtering for recommending research papers. The hybrid approaches combine the strengths of each algorithm to address their individual weaknesses. We evaluated our algorithms through both offline experiments on a database of 102,000 research papers, and an online experiment with 110 users. Our results show that users value recommendations of papers, that the hybrid algorithms can be successfully combined, that different algorithms are more suitable for recommending different kinds of papers, and that users with different levels of experience perceive recommendations differently. Our results lead us to a completely tailored research paper recommender system.

Referências

BREESE, J., et al. Empirical Analysis of Predictive Algorithms for Collaborative Filtering. Conference on Uncertainty in Artificial Intelligence, 1998, Madison, Wisconsin. Proceedings. 1998.

HERLOCKER, J., et al. An Algorithmic Frame work for Performing Collaborative Filtering. ACM SIGIR Conference on Research and Development in Information Retrieval, 1999, Berkeley, CA. Proceedings. 1999.

KAMBA, T., et al. The Krakatoa Chronicle: An Interactive Personalized Newspaper on the Web. International World Wide Web Conference, 4, 1995, Boston. Proceedings. O'Reilly & Associates, 1995.

MCNEE, S., et al. On the Recommending of Citations for Research Papers. Computer Supported Cooperative Work Conference, 2002, New Orleans, Louisiana - USA. Proceedings. ACM, 2002.

RESNICK, P., et al. GroupLens: An open architecture for collaborative filtering of Netnews. Computer Supported Collaborative Work Conference, 1994, Chapel Hill, North Carolina - USA. Proceedings. 1994.

SHARDANAND, U.; MAES, P. Social inf ormation Filtering: Algorithms for automating "word of mouth". Conference on Human Factors in Computing Systems, 1995, New York. Proceedings. 1995.

TORRES, R., et al. Enhancing Digital Libraries with TechLens+. Joint Conference on Digital Libraries (JCDL), 2004, Tucson, Arizona - USA. Proceedings. 2004.