Personalized global citation recommendation with diversification awareness

Citation recommendation helps researchers perform reference searching more efficiently. Traditional methods often focus separately on diversification and personalization, each with unique advantages and limitations. In this study, we propose a new citation recommendation paradigm, personalized global citation recommendation with diversification awareness (PGCR-DA), which integrates the two approaches to generate more relevant candidate citations. Our work involved two major tasks. The first task involves generating a pool of diversified candidate citations for each target paper, by using the Random Walk with Restart on a constructed heterogeneous graph to identify the first relevant citation. The remaining diversified candidates are returned by using the Maximal Marginal Relevance model, where diversified citations are obtained based on a two-dimensional, i.e., the semantic space and publication date of the paper, diversification strategy. The second task focuses on personalization, where the ranking list obtained in the first task is reranked by modeling fine-grained and dynamic user preferences, informed by the analysis of both the textual and entity space from the users’ previous publications. Preliminary experiments on the AAN and DBLP datasets verify our hypothesis that diversification and personalization can be effectively integrated through our approach. The results further demonstrate that PGCR-DA outperforms the competitive global citation recommendation methods with respect to a series of metrics.