The role of sentiment in the stock market

Objectives: There is a large and rapidly growing body of literature examining the impact of investors’ sentiment on financial markets, especially the predictive power of internet message postings. The empirical studies commonly employ distinct classifier machine learning algorithms to extract sentiment proxies from the huge quantity of text messages published in the news, in social media or on internet message boards (Antweiler and Frank, 2004; Arias et al., 2013 or Kim and Kim, 2014). These sentiment proxies are associated with specific words or expressions identified by rules or lexicons. We suppose that sentiment changes the risk perceptions of economic agents and therefore expectations about a final return.

Background: Risk perception is subjective (Sitking and Weingard, 1995; Weber, 2004; Ricciardi, 2008) and this individual assessment can be influenced by media coverage or the judgment of others, meaning that (for example) the notions of crowd psychology, herd behavior (Renn, 1990; Ricciardi, 2008) or social mood (Nofsinger, 2005) become relevant. In the context of this research, the sentiment of society changes investors’ risk perception.

Data and Method: The paper augments Solnik‘s (1983) model of International Arbitrage Pricing Theory (IAPT) (empirically tested by Armstrong et al. 2012). We employ panel data mixed-effects models and identify links between stock returns and volatility, market risks, exogenous market shocks, firm specifics, and sentiment, where sentiment is represented by news posted on 20 sources ( mainly Reuters, Bloomberg, the Wall Street Journal, LA Times, CNBC, Forbes, Business Insider, and Yahoo Finance). We use intraday data of S&P 500 companies in the years 2013–2016.

Expected Results: Our empirical strategy is based on the multifactor asset pricing model in the domain of the IAPT. We show that the changes in sentiment represent specific company and market risks and provide an extended capital asset pricing model for inefficient markets.

 Keywords: Stock returns; stock volatility; International Arbitrage Pricing Theory; sentiment analysis; social networks

 JEL:  G12 - Asset Pricing, G14 - Information and Market Efficiency, G15 - International Financial Markets