Social media, political uncertainty, and stock markets
- PDF / 806,166 Bytes
- 17 Pages / 439.37 x 666.142 pts Page_size
- 66 Downloads / 250 Views
Social media, political uncertainty, and stock markets Rui Fan1 · Oleksandr Talavera2 · Vu Tran3
© Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract This study proposes a new measure of firm-level uncertainty exposure around important political events. More specifically, we construct a degree of (dis)agreement among social media users who jointly mention firms and politicians. We study a sample of over 23 million tweets mentioning both a firm from the S&P 500 composite and ‘Trump’ from October 2016 to May 2017. We then analyze the relationship between the (dis)agreement measure and individual stock features. The results suggest that increased disagreement among such tweets is associated with heightened stock price volatility and trading volume. This link is observed before the US Presidential Inauguration in January 2017 but not afterwards. The finding is confirmed by further robustness checks based on filtered tweets with policy keywords and policy-sensitive industries. Keywords Twitter · US election · Stock market · Investor sentiment · Text classification · Computational linguistics JEL Classification D72 · G12 · G14 · L86
1 Introduction Political events are known to affect stock markets (e.g. Bialkowski et al. 2008; Pastor and Veronesi 2013; Kelly et al. 2016). This link often arises from the policy uncertainty associated with political events. However, not all stocks are affected by political uncertainty in the same way (e.g. Hill et al. 2019). This work proposes a new measure of firm-level political uncertainty using the agreement among social media users around important political events. Our social media data contain Twitter messages mentioning both a S&P 500 firm name and ‘Trump’ covering a period around the 2016 US Presidential Election and Trump’s Inauguration. * Rui Fan [email protected] 1
School of Management, Swansea University, Fabian Way, Swansea SA1 8EN, UK
2
Birmingham Business School, University of Birmingham, Edgbaston Park Road, Birmingham B15 2TY, UK
3
ICMA Centre, Henley Business School, University of Reading, Whiteknights, Reading RG6 6BA, UK
13
Vol.:(0123456789)
R. Fan et al.
Our study connects several different strands of literature. First, we contribute to the literature about the relationship among politics, policy uncertainty, and stock prices. For example, Pastor and Veronesi (2013) model a relationship between political uncertainty and a stock’s risk premium in which the stock price volatility and the risk premium both increase before a change in policy regimes. Baker et al. (2016) and Kelly et al. (2016) provide empirical evidence about an association between policy uncertainty and financial market valuation and price volatility. Notably, the linkage is heterogeneous across industries (Baker et al. 2016). Hill et al. (2019) find varied impacts of political uncertainty associated with the 2016 Brexit Referendum on the UK firms. To the best of our knowledge, there is no prior study utilizing the vast amount of information in social me
Data Loading...