Technical paper recommendation: A study in combining multiple information sources

The growing need to manage and exploit the proliferation of online data sou rces is opening up new opportunities for bringing people closer to the reso urces they need. For instance, consider a recommendation service through wh ich researchers can receive daily pointers to journal papers in their field s of interest. We survey some of the known approaches to the problem of tec hnical paper recommendation and ask how they can be extended to deal with m ultiple information sources. More specifically, we focus on a variant of th is problem - recommending conference paper submissions to reviewing committ ee members - which offers us a testbed to try different approaches. Using W HIRL - an information integration system - we are able to implement differe nt recommendation algorithms derived from information retrieval principles. We also use a novel autonomous procedure for gathering reviewer interest i nformation from the Web. We evaluate our approach and compare it to other m ethods using preference data provided by members of the AAAI-98 conference reviewing committee along with data about the actual submissions.