%0 Journal Article
%T Author每Subject每Topic model for reviewer recommendation
%A Chong Chen
%A Haikun Mou
%A Jian Jin
%A Qian Geng
%J Journal of Information Science
%@ 1741-6485
%D 2019
%R 10.1177/0165551518806116
%X Interdisciplinary studies are becoming increasingly popular, and research domains of many experts are becoming diverse. This phenomenon brings difficulty in recommending experts to review interdisciplinary submissions. In this study, an Author每Subject每Topic (AST) model is proposed with two versions. In the model, reviewers＊ subject information is embedded to analyse topic distributions of submissions and reviewers＊ publications. The major difference between the AST and Author每Topic models lies in the introduction of a ＆Subject＊ layer, which supervises the generation of hierarchical topics and allows sharing of subjects among authors. To evaluate the performance of the AST model, papers in Information System and Management (a typical interdisciplinary domain) in a famous Chinese academic library are investigated. Comparative experiments are conducted, which show the effectiveness of the AST model in topic distribution analysis and reviewer recommendation for interdisciplinary studies
%K Author每Subject每Topic model
%K expert finding
%K expert recommendation
%K reviewer assignment
%K reviewer recommendation
%U https://journals.sagepub.com/doi/full/10.1177/0165551518806116