Widespread Worry and the Stock Market

By Eric Gilbert, K. G. Karahalios. 2010

319 citations recorded by the source corpus.

Our emotional state influences our choices. Research on how it happens usually comes from the lab. We know relatively little about how real world emotions affect real world settings, like financial markets. Here, we demonstrate that estimating emotions from weblogs provides novel information about future stock market prices. That is, it provides information not already apparent from market data. Specifically, we estimate anxiety, worry and fear from a dataset of over 20 million posts made on the site LiveJournal. Using a Granger-causal framework, we find that increases in expressions of anxiety, evidenced by computationally-identified linguistic features, predict downward pressure on the S&P 500 index. We also present a confirmation of this result via Monte Carlo simulation. The findings show how the mood of millions in a large online community, even one that primarily discusses daily life, can anticipate changes in a seemingly unrelated system. Beyond this, the results suggest new ways to gauge public opinion and predict its impact.

Subfields: Social Psychology, Statistical and Nonlinear Physics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Social Psychology

In Statistical and Nonlinear Physics

Citations in the corpus

Twitter mood predicts the stock market (2010, background): “Over the past 5 years significant progress has been made in sentiment tracking techniques that extract indicators of public mood directly from social media content such as blog content [10], [12], [15], [17] and in particular large-scale Twitter feeds [22].”
Social signals and algorithmic trading of Bitcoin (2015, methodology): “Since our multidimensional analysis is robust to confounds between multiple time series, the ﬁndings of impulse analysis can be integrated in a Combined strategy based on a voting mechanism.”
Sentiment analysis of Twitter data for predicting stock market movements (2016, background): “Gilbert and Karahalios [9] have found out that increases in expressions of anxiety, worry and fear in weblogs predict downward pressure on the S&P 500 index.”
Natural Language Processing in Accounting, Auditing and Finance: A Synthesis of the Literature with a Roadmap for Future Research (2016, methodology): “The results were compiled into an Anxiety Index covering 174 trading days, and then compared with stock prices, using Granger causality analysis (Gilbert & Karahalios, 2010).”
A survey of the applications of text mining in financial domain (2016, background): “Various Studies of Phishing Detection Study Dataset Model Performance Measure Abdelhamid et al. (2014) Millersmiles/ PhishTank Associative Rule Accuracy Chen et al. (2011) Millersmiles DT/ NN/ SVM Accuracy He et al. (2011) Millersmiles\ PhishTank\ 3Sharp SVM True Positive/ False Positive Aburrous et”
Procedia Social and Behavioral Sciences (unknown): “Gilbert and Karahalios (2010) used over 20 million posts from the LiveJournal website to create an index of the US national mood, which they call the Anxiety Index.”
Analyzing Stock Market Movements Using Twitter Sentiment Analysis (2012, methodology): “We have made use of GCA in similar fashion as [4], [6] This is to test if one time series is significant in predicting another time series.”
Emotional State and Market Behavior (2013, unknown): “Gilbert and Karahalios (2009) find that the level of anxiety of posts on the blog site Live Journal predicts price declines.”
Tensor-Based Learning for Predicting Stock Movements (2015, unknown): “…and Titman 1993), whereas modern behavioral finance is interested in the shortterm shock of sentimental factors and event-specific factors (Bollen, Pepe, and Mao 2011; Frank and Antweiler 2004; Gilbert and Karahalios 2010; Schumaker and Chen 2009b; Tetlock, Saar-Tsechansky, and Macskassy 2008).”
A Tensor-Based Information Framework for Predicting the Stock Market (2016, background): “Gilbert and Karahalios [2010] reported that increased levels of anxiety, worry, and fear produced downward pressure on the Standard and Poors (S&P) 500 index.”
How (Not) to Predict Elections (2011, background): “…predictions of flu epidemics [5], [6]), business (e.g., prediction of box-office success of movies [7] and product marketability [4]), economics (e.g., predictions on stock market trends and housing market trends [3], [8], [9]), and politics (e.g., trends in public opinion [10]), to name a few.”
The language that gets people to give: phrases that predict success on kickstarter (2014, background): “Emotions expressed via language even act as good predictors of future stock market prices, where emotions were estimated from blog posts [19].”
The Tweets They Are a-Changin: Evolution of Twitter Users and Behavior (2014, background): “2010), and even using aggregated data from Twitter to predict the behavior of real-world phenomena such as the stock market (Gilbert and Karahalios 2010).”
Measuring the Information Content of Financial News (2016, background): “…et al., 2013; Luss and d’Aspremont, 2015; Ding et al., 2015), ﬁrm reports (Kogan et al., 2009; Li, 2010; Lee et al., 2014; Qiu et al., 2014) and web content, such as tweets (Bollen et al., 2011; Vu et al., 2012) and forum posts (Das and Chen, 2007; Gilbert and Karahalios, 2010) have been studied.”
The power of prediction with social media (2013, background): “Other researchers (e.g., Gilbert and Karahalios, 2010; Bollen et al., 2011a and 2011b; or Zhang et al., 2011) have shown that public mood measured through social media (e.g., LiveJournal or Twitter) is somewhat related to stock market movements: for instance, anxiety or fear tend to predate…”
The effect of news and public mood on stock movements (2014, background): “Gilbert and Karahalios [18] Anxiety, worry, fear General”
Beyond Sentiment: The Manifold of Human Emotions (2012, background): “Examples include tracking public opini on [11], estimating political sentiment [15], and correlating sentiment with the stock market [3].”