Electronic copy available at: https://ssrn.com/abstract=3197874 Momentum, Mean-Reversion and Social Media: Evidence from StockTwits and Twitter ∗ Shreyash Agrawal † , Pablo D. Azar ‡ , Andrew W. Lo § , Taranjit Singh ¶ This Draft: 12 July 2018 We analyze the relation between stock market liquidity and real-time measures of sentiment obtained from the social-media platforms StockTwits and Twitter. Linear regression analysis shows that extreme sentiment corresponds to higher demand and lower supply of liquidity, with negative sentiment having a much larger effect on demand and supply than positive sentiment. An intraday event study shows that booms and panics end when bullish and bearish sentiment reach extreme levels, respectively. After extreme sentiment, prices become more mean-reverting and spreads narrow. To quantify the magnitudes of these effects, we conduct a historical simulation of a market-neutral mean-reversion strategy that uses social- media information to determine its portfolio allocations. Our results suggest that the demand and supply of liquidity are influenced by investor sentiment, and that market makers who can keep their transaction costs to a minimum are able to profit by using extreme bullish and bearish emotions in social media as a real-time barometer for the end of momentum and a return to mean reversion. Keywords: Sentiment; Market Liquidity; Social Media; Twitter; StockTwits; Mean Reversion JEL classification: G11, G12 * We thank James Crane-Baker at Psychsignal and Pierce Crosby at Stocktwits for providing the social- media sentiment data used in this study, and Shomesh Chaudhuri, Katy Kaminski, and Amir Khandani for helpful discussion and comments. We thank Jayna Cummings for editorial assistance. Research support from the MIT Laboratory for Financial Engineering is gratefully acknowledged. † MIT Laboratory for Financial Engineering, shreyash@mit.edu (e-mail). ‡ MIT Department of Economics and Laboratory for Financial Engineering, pabloazar@gmail.com (e- mail). § MIT Sloan School of Management, Laboratory for Financial Engineering, and Computer Science and Artificial Intelligence Laboratory, alo-admin@mit.edu (e-mail). Corresponding author. ¶ MIT Laboratory for Financial Engineering, taranjitsingh96@gmail.com (e-mail).