X-sentiment and stock illiquidity: A convex relationship
Abstract/Description
Using a textual analysis of over 12.8 million tweets published by S&P 500 companies from January 2015 to December 2022, we developed a novel measure for X (formerly Twitter) sentiment. We find that sentiment, scaled by the number of tweets per day, is negatively associated with the Twitter Economic Uncertainty (Baker et al., 2021) and Economic Policy Uncertainty (Baker et al., 2016) indices, indicating that firms’ voluntary disclosures using their X handles correlate with negative sentiments, on average, amid an increase in economic uncertainty. We find a nonlinear relationship between sentiment and stock illiquidity, as a rise in sentiment per tweet is associated with a convex decline in the rate of change in the bid-ask spread. These results are robust to different measures of illiquidity and alternate panel regressions. Our findings imply that the strength of the sentiment expressed in tweets and the frequency of firm disclosures can reduce information asymmetry. However, this effect diminishes with the frequency of disclosures. This study helps clarify how social media sentiment affects market dynamics, particularly stock illiquidity.
Keywords
Investor sentiment, Twitter, X, illiquidity, information asymmetry, uncertainty
Track
Finance
Session Number/Theme
1A: Finance
Session Chair
Dr. Adnan Haider; Dr. Aitzaz Ahsan Alias
Start Date/Time
30-5-2024 1:50 PM
End Date/Time
30-5-2024 3:20 PM
Location
MCS – 3 AMAN CED Building
Recommended Citation
Khawaja, M. Z., & Ahmed, S. (2024). X-sentiment and stock illiquidity: A convex relationship. 3rd IBA SBS International Conference 2024. Retrieved from https://ir.iba.edu.pk/sbsic/2024/program/4
COinS
X-sentiment and stock illiquidity: A convex relationship
MCS – 3 AMAN CED Building
Using a textual analysis of over 12.8 million tweets published by S&P 500 companies from January 2015 to December 2022, we developed a novel measure for X (formerly Twitter) sentiment. We find that sentiment, scaled by the number of tweets per day, is negatively associated with the Twitter Economic Uncertainty (Baker et al., 2021) and Economic Policy Uncertainty (Baker et al., 2016) indices, indicating that firms’ voluntary disclosures using their X handles correlate with negative sentiments, on average, amid an increase in economic uncertainty. We find a nonlinear relationship between sentiment and stock illiquidity, as a rise in sentiment per tweet is associated with a convex decline in the rate of change in the bid-ask spread. These results are robust to different measures of illiquidity and alternate panel regressions. Our findings imply that the strength of the sentiment expressed in tweets and the frequency of firm disclosures can reduce information asymmetry. However, this effect diminishes with the frequency of disclosures. This study helps clarify how social media sentiment affects market dynamics, particularly stock illiquidity.
