Folksonomy based socially-aware recommendation of scholarly papers for conference participants

Abstract

Due to the significant proliferation of scholarly papers in both conferences and journals, recommending relevant papers to researchers for academic learning has become a substantial problem. Conferences, in comparison to journals have an aspect of social learning, which allows personal familiarization through various interactions among researchers. In this paper, we improve the social awareness of participants of smart conferences by proposing an innovative folksonomy-based paper recommendation algorithm, namely, Socially-Aware Recommendation of Scholarly Papers (SARSP). Our proposed algorithm recommends scholarly papers, issued by Active Participants (APs), to other Group Profile participants at the same smart conference based on similarity of their research interests. Furthermore, through computation of social ties, SARSP generates effective recommendations of scholarly papers to participants who have strong social ties with an AP. Through a relevant real-world dataset, we evaluate our proposed algorithm. Our experimental results verify that SARSP has encouraging improvements over other existing methods.