BioCLink: A Probabilistic Approach for Improving Genomics Search with Citation Links

Combination of multiple evidences has been shown to be effective in genomics literature retrieval. Citation information is an intuitive evidence for facilitating literature retrieval. Previous research on citation analysis has demonstrated that useful linkage information can be extracted from the citation graph. However, the question of how the combination of citation evidence and content evidence should be done to maximize retrieval accuracy still remains largely unanswered. In this paper, we propose BioCLink, a new probabilistic approach that integrates citation evidence into content-based weighting function for improving genomics literature retrieval performance. Based on findings of our previous study, a strategy for modeling citation evidence is proposed. BioCLink provides the combination of content and citation evidences with a theoretical support. Moreover, exhaustiveparameter tuning can be avoided using BioCLink. Extensive experiments on TREC 2006 and 2007 Genomics collections demonstrate the advantages and effectiveness of our proposed methods.