Investigating the impact of sentiments on stock returns: evidence from reactions to social media content

Due to the increasing growth of social networks in recent years, investors in various markets, in addition to reviewing and analyzing classic market information, also pay attention to news and information published on social networks. By examining and evaluating the relationship between news and information published on social networks and changes in stock prices, it is possible to understand the impact of the information on stock prices and predict the future trend.In this article, using the methods of sentiment analysis and text mining, the impact of public thoughts and feelings caused by news on the Internet and cyberspace on stock prices is examined. The information used in this research includes content published on the social network Twitter about stocks and real stock price data of the top 5 companies on the US stock exchange. Using the presented method, general feelings about a text are estimated and a general score is considered for it. Then, using back testing methods and adopting different trading strategies, the impact of these emotions on the share price trend will be examined and the obtained results will be compared with and without the effect of emotion analysis. According to the results of this study, the effectiveness of strategies based on sentiments analysis is significantly higher than technical analysis-based methods.