Analyzing the impact of investor sentiment in social media to stock return: Survival analysis approach

Abstract

In the era of information technology, stock related information can be easily found on the internet, especially on social media. Thus, data in social media hold an important information to predict the movement of stock price. In addition, the research about the time of stock fulfillment, that is the time until stock gives the expected return, is very rare. For this reason, in this research, we will use Survival Analysis to model time aspect of trading strategies using investor sentiment as the predictor. The result shows that investor sentiment in Stockbit can be used as the predictor of return in Survival Analysis Model we developed and can be used as an alternative method to make stock buying and selling process. We also find Cumulative Twitter Investor Sentiment Hazard (CTIS) ratio of less than one indicates that an increase of CTIS will reduce the hazard.