Title: Measuring gender differences in personalities through natural language in the labor force
Authors: Dania Eugenidis - Justus-Liebig-University Giessen (Germany) [presenting]
David Lenz - Justus-Liebig University Giessen (Germany)
Abstract: Gender stereotypes still play a major role in the perception and representation of people in the workplace. Traditional measures, such as questionnaires, often lack objectivity and thus struggle to provide the full picture. However, evidence-based policymaking requires accurate indicators of gender inequalities to promote equality. This framework depicts the first-ever study examining the external portrayal of gender stereotypes on a company level using publicly available big data. Specifically, nearly one million company websites are called in using natural language processing. Shortcomings of traditional quantitative measures are to be overcome regarding timeliness, granularity and cost efficiency. That way, it is possible for the first time to conduct a fully automated, objective and almost comprehensive analysis of the linguistic portrayal of gender in a corporate context. A subsequent comparison to the literature takes place by contextualizing the gender stereotype measures following the personality traits of the Big Five-factor model and their sublevels. The results of the statistical analysis indicate significant stereotypes within personality traits for large portions of the sample. These differences in gender presentation are mostly consistent with those found in the literature, which serve as a validation for the presented framework.