Abstract: Using novel data on investors' social interactions, we document sentiment contagion as a direct consequence of social learning in the Bitcoin market. Our findings suggest that the social learning process is inefficient, as investors respond positively to social sentiment, but social sentiment does not positively predict returns. Echo chamber effect and selective interpretation of information may simultaneously contribute to such inefficiency. We further confirm that sentiment contagion is not a sideshow: at the individual level, sentiment contagion predicts the direction of trading conditional on its occurrence; at the Bitcoin market level, the aggregated sentiment contagion index positively predicts market trading volume and volatility. Moreover, we highlight the error-prone nature of social learning, wherein the socially constructed optimism predicts Bitcoin crashes. Finally, we establish a link between social learning and bubbles: the elevated propagation of optimism is highly correlated with the trading volume.
Discussant: Adlai Fisher, University of British Columbia
Abstract: A significant portion of information shared in earnings calls is conveyed through verbal communication by corporate managers. However, quantifying the extent of new information provided by managers poses challenges due to the unstructured nature of human language and the difficulty in gauging the market’s existing knowledge. In this study, we introduce a novel measure of information content (Human-AI Differences, HAID) by exploiting the discrepancy between answers to questions at earnings calls provided by corporate executives and those given by several context-preserving Large Language Models (LLM) such as ChatGPT, Google Bard, and an open source LLM. HAID strongly predicts stock liquidity, abnormal returns, number of analysts’ forecast revisions, analyst forecast accuracy following these calls, and propensity of managers to provide management guidance, consistent with HAID capturing new information conveyed by managers. Overall, our results highlight the importance of using LLM as a tool to help investors unveil the veiled – penetrating the information layers and unearthing hidden insights.
