Exploiting Potential Citation Papers in Scholarly Paper Recommendation

To help generate relevant suggestions for researchers, recommendation systems have started to leverage the latent interests in the publication profiles of the researchers themselves. While using such a publication citation network has been shown to enhance performance, the network is often sparse, making recommendation difficult. To alleviate this sparsity, we identify "potential citation papers" through the use of collaborative filtering. Also, as different logical sections of a paper have different significance, as a secondary contribution, we investigate which sections of papers can be leveraged to represent papers effectively. On a scholarly paper recommendation dataset, we show that recommendation accuracy significantly outperforms state-of-the-art recommendation baselines as measured by nDCG and MRR, when we discover potential citation papers using imputed similarities via collaborative filtering and represent candidate papers using both the full text and assigning more weight to the conclusion sections.