Does deep learning help topic extraction? A kernel k-means clustering method with word embedding

Yi Zhang, Jie Lu, Feng Liu, Qian Liu, Alan L. Porter, Hongshu Chen, Guangquan Zhang

Abstract: Highlights • A novel topic extraction method incorporated with a kernel k-means model and a word embedding model. • The incorporation of word embedding techniques in data pre-processing for topic extraction. • A polynomial kernel function-based k-means model for effectively conducting bibliometric data-oriented topic extraction. • Empirical insights into both overlapping and diverse research interests among three top-tier bibliometric journals. Abstract Topic extraction presents challenges for the bibliometric community, and its performance still depends on human intervention and its practical areas. This paper proposes a novel kernel k-means clustering method incorporated with a word embedding model to create a solution that effectively extracts topics from bibliometric data. The experimental results of a comparison of this method with four clustering baselines (i.e., k-means, fuzzy c-means, principal component analysis, and topic models) on two bibliometric datasets demonstrate its effectiveness across either a relatively broad range of disciplines or a given domain. An empirical study on bibliometric topic extraction from articles published by three top-tier bibliometric journals between 2000 and 2017, supported by expert knowledge-based evaluations, provides supplemental evidence of the method’s ability on topic extraction. Additionally, this empirical analysis reveals insights into both overlapping and diverse research interests among the three journals that would benefit journal publishers, editorial boards, and research communities.