The Fault in the Stars : Exploring Employee Sentiment and Stock Returns through Textual Analysis

Prior research has used Glassdoor.com's five-star rating system to measure employee satisfaction and explore its relationship to stock returns. We demonstrate how, due to a 2012 internal Glassdoor.com policy change, this crowd sourced data suffers from abnormalities that limits its usefulness. To account for these issues, we employ textual analysis via multinominal inverse regression to create monthly firm-specific satisfaction measures for public US firms from 2009-2019. We find evidence that using raw star ratings biases coefficient estimates toward zero in both cross-sectional and portfolio analyses, implying the relationship between employee satisfaction and abnormal returns may be understated in the literature