Intraday Mean Reversion Signals from StockTwits and Twitter Activity
Summary
The study examines whether news and social-media sentiment relate to intraday stock liquidity and returns. It combines stock-linked news sentiment with minute-level Twitter and StockTwits measures, then uses regressions and event studies to analyze liquidity indicators and unusually strong sentiment readings. The reported patterns include a larger liquidity response to negative than positive social sentiment and high momentum before extreme sentiment followed by mean reversion. The event analysis also associates extreme sentiment with lower spreads afterward, though that spread result is not statistically significant.
A market-neutral strategy rebalances every 30 minutes among the 500 stocks with the highest average trading volume over the previous 200 days. It shorts recent winners and buys recent losers, assigning twice the weight to names with elevated message activity. In the historical sample, the article reports higher annualized returns for this social-media version than for its baseline; tighter volume limits reduced returns for both. The results are before realistic full trading costs, and the authors note that message-market feedback and user identities were not modeled. High turnover may make implementation costly.
Key ideas
- Negative social-media sentiment is reported to affect liquidity more strongly than positive sentiment.
- Extreme social-media readings tend to follow strong momentum and precede intraday mean reversion.
- The tested market-neutral strategy buys recent losers and shorts recent winners every 30 minutes.
- It increases weights for stocks with unusually high Twitter and StockTwits activity.
- The reported historical outperformance is limited by trading costs, turnover, and unresolved causality.
Tags
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.