Herding the crowds: how sentiment affects crowdsourced earnings estimates

This study investigates the impact of firm-level investor sentiment derived from Twitter and news media on herding behavior among contributors on Estimize, a leading platform for crowdsourced earnings forecasts. The findings show that sentiment gleaned from tweets and news media content positively influences herding among Estimize contributors. Notably, herding intensifies when Twitter and news sentiment polarities align, while divergent sentiment polarities diminish this herding effect. Additionally, the analysis indicates that firms with investment-grade ratings and those characterized by low valuation uncertainty are particularly prone to sentiment-driven herding. Importantly, positive sentiment is identified as having a more potent influence on herding behavior than negative sentiment. By focusing on Estimize contributors, this study offers insights into how firm-level sentiment cues shape the crowd’s herding behavior, offering new perspectives on how different media sources shape the wisdom of the crowd.