Topic-Based PageRank on Author Cocitation Networks

Ranking authors is vital for identifying a researcher's impact and standing within a scientific field. There are many different ranking methods (e.g., citations, publications, h-index, Page Rank, and weighted Page Rank), but most of them are topic-independent. This paper proposes topic-dependent ranks based on the combination of a topic model and a weighted Page Rank algorithm. The author-conference-topic (ACT) model was used to extract topic distribution of individual authors. Two ways for combining the ACT model with the Page Rank algorithm are proposed: simple combination (I_PR) or using a topic distribution as a weighted vector for Page Rank (PR_t). Information retrieval was chosen as the test field and representative authors for different topics at different time phases were identified. Principal component analysis (PCA) was applied to analyze the ranking difference between I_PR and PR_t.