An analysis of the impact of President Trump’s tweets on the DJIA and S&P 500 using machine learning and sentiment analysis

Abstract

We analyze the immediate impact of President Trump’s tweets on two US stock market indices using a 30-minute event window for each tweet and intra-day market data. The tweets and intra-day market data, are used to study market reactions using sentiment analysis, and machine learning (ML) classification and regression. The results show a significant negative reaction when President Trump tweeted during open market hours. We also found that tweets with a strong positive or strong negative sentiment had positive market reactions. ML regressors use the tweets and market data to predict the post-tweet market index averages and post-tweet market trends.