主题：Text analysis can talk---when we use journal H-index to evaluate academic papers.
Journal H-index as a research assessment tool has been attracting increasing interest recently. In this paper, we build and discuss models to predict academic outputs regarding the H-index and study the potential gender effects. We create a novel dataset with academic papers with their text content, H-indices of the journal where the article was published, gender of the author(s), number of the author(s), and other information, and apply Term Frequency–Inverse Document Frequency (tf–idf) vectorization and other Natural Language Processing (NLP) tools to transfer text content into numerical values as model inputs. With the text corpus we generated, we built a functional model to predict the quality of economics papers regarding the journal H-index and find evidence against gender discrimination in academic paper publishing.
主讲人介绍：Dr. Yong Bian earned her Ph.D. in Economics from University of Missouri—Columbia in May 2021. Her research interest is applied econometrics especially focusing on machine learning applications in economics and finance. She has papers published in Frontiers in Psychology this year and several other papers under revision now. She also holds a master’s degree in economics from the Chinese University of Hong Kong and a bachelor’s degree in statistics from the Central University of Finance and Economics.