Trade Sentiment and the Stock Market: New Evidence Based on Big Data Textual Analysis of Chinese Media

We present a novel trade sentiment index (TSI) based on textual analysis and machine learning applied to a big data pool. The index assesses the positive or negative tone of the Chinese media coverage and evaluates its capacity to explain the behavior of 60 global equity markets. The difference in tone explains stock price variability better than pure counting of keywords, and the application of the algorithm to social media explains variability better than application to traditional media. Looking at the behavior of the different equity markets, we find that there are no winners of the trade war. 

Read the paper, "Trade Sentiment and the Stock Market: New Evidence Based on Big Data Textual Analysis of Chinese Media": 
https://www.hks.harvard.edu/centers/mrcbg/publications/awp/awp158