Extracting News Sentiment and Establishing Its Relationship with the S&P 500 Index

Sentiment analysis has been shown to be a useful tool for quantitative analysis in the world of finance. Researchers have shown that the sentiment picked up from the news media can be correlated with movement of the stock market. Here we use the Harvard General Inquirer to determine the sentiment present in Reuter’s articles. After first generating positive and negative sentiment data we use the Kalman filter for smoothing. We then establish a correlation between the movement of the S&P 500 and sentiment. The results indicate that correlations between the sentiment in the news and the S&P index are strong for five of the seven years analyzed.