Market Trend Prediction using Sentiment Analysis: Lessons Learned and Paths Forward

TL;DR

This paper explores the use of sentiment attitudes and emotions from financial news and social media to predict stock market movements, revealing limited causality but potential for improved prediction accuracy when emotions are incorporated.

Contribution

It provides an extensive analysis of sentiment's role in market prediction, highlighting the limited causality of attitudes and the conditional usefulness of emotions as predictive features.

Findings

Sentiment attitudes generally do not Granger-cause stock price changes.

Sentiment emotions sometimes Granger-cause stock movements but not universally.

Incorporating sentiment emotions can improve prediction accuracy for certain stocks.

Abstract

Financial market forecasting is one of the most attractive practical applications of sentiment analysis. In this paper, we investigate the potential of using sentiment \emph{attitudes} (positive vs negative) and also sentiment \emph{emotions} (joy, sadness, etc.) extracted from financial news or tweets to help predict stock price movements. Our extensive experiments using the \emph{Granger-causality} test have revealed that (i) in general sentiment attitudes do not seem to Granger-cause stock price changes; and (ii) while on some specific occasions sentiment emotions do seem to Granger-cause stock price changes, the exhibited pattern is not universal and must be looked at on a case by case basis. Furthermore, it has been observed that at least for certain stocks, integrating sentiment emotions as additional features into the machine learning based market trend prediction model could improve its accuracy.