Applying content-based similarity measure to author co-citation analysis

This study proposed a novel author similarity measure in author co-citation analysis (ACA). Unlike other ACA studies, we used citing sentences to reflect topical relatedness of authors. In our research, we extended traditional approaches by adopting Word2Vec, one of deep learning methods, to measure author similarity. We also conducted in-depth network analysis of author maps. The results of Word2Vec-based author map revealed more specific sub-disciplines and the important authors in perspective of topical influence than traditional approach does. Our method allows for more sophisticated analysis than the traditional ACA approach by providing a more in-depth understanding and the specific structure of a discipline