Combining Citation Network Information and Text Similarity for Research Article Recommender Systems

Researchers often need to gather a comprehensive set of papers relevant focused topic, but this is difficult and time-consuming using existing search methods. For example, keyword searching suffers from difficulties with synonyms multiple meanings. While some automated research-paper recommender systems exist, these typically depend on either researcher’s entire library or just single paper, resulting in quite broad narrow search. With issues mind, we built new system that utilizes both citation information textual similarity abstracts provide highly results. The input one more related papers, our searches for are closely the set. This framework helps researchers particular topic interest, allows control over which cross-section literature located. We show effectiveness by it recreate references review papers. also its utility as general metric between scientific articles performing unsupervised clustering sets articles. release an implementation, ExCiteSearch (bitbucket.org/mmmontemore/excitesearch), allow apply locate