Context-based Collaborative Filtering for Citation Recommendation

Context-based Collaborative Filtering for Citation Recommendation

Abstract— Citation recommendation is an interesting and significant research area as it solves information overload in academia by automatically suggesting relevant references for a research paper. Recently, with the rapid proliferation of information technology, research papers are rapidly published in various conferences and journals. This makes citation recommendation a highly important and challenging discipline. In this paper, we propose a novel citation recommendation method that uses only easily-obtained citation relations as source data. The rationale underlying this method is that, if two citing papers are significantly co-occurring with the same citing papers, < Final Year Projects 2016 > they should be similar to some extent. Based on the above rationale, an association mining technique is employed to obtain paper representation of each citing paper from the citation context. Then, these paper representations are pairwise compared to compute similarities between citing papers for collaborative filtering. We evaluate our proposed method through two relevant real-world datasets. Our experimental results demonstrate that the proposed method significantly outperforms the baseline method in terms of precision, recall, and F1 as well as MAP and MRR, which are metrics related to rank information in the recommendation list.