Predicting Sector Index Movement with Microblogging Public Mood Time Series on Social Issues

This paper develops a technique that unfolds public mood on social issues from real-time social media for sector index prediction. We first propose a low-dimensional support vector machine (SVM) classifier using surrounding information for twitter sentiment classification. Then, we generate public mood time series by aggregating message-level weighted daily mood (WDM) based on the sentiment classification results. Lastly, we evaluate our method against the real stock index in two kinds of time periods (fluctuating and monotonous) separately using static cross-correlation coefficient (CCF) and dynamic vector auto-regression (VAR). The experiments on “food safety” issue show that the proposed WDM method outperforms the wordlevel baseline method in predicting stock movement, especially during fluctuating period.