Headlines or Hashtags? The battle in social media for investor sentiment in the stock market

Abstract

This study tackles the complex task of measuring investor sentiment, a latent variable often measured through various proxies. The focus here is on textual sentiment extracted from online sources, specifically news media and social media sentiment. The central inquiry is whether these proxies are equivalent indicators of investor sentiment. Employing firm-level daily sentiment scores for DJIA stocks and leveraging Granger causality and transfer entropy, the research investigates the dynamics of information flow between these proxies. The findings show a prevailing pattern: information predominantly flows from social media to news for the majority of stocks while a reverse relationship is established for some stocks. The variations across stocks suggest that these proxies do not uniformly capture the same underlying phenomena. The study shows the significant role of social media in shaping news media sentiment and prompts considerations about regulating social media platforms in the context of their impact on financial markets.