Estimating the impact of domain-specific news sentiment on financial assets

The influence of news on financial markets has been studied by extracting opinions and sentiment from text using content analysis and natural language processing techniques, and then using this measure to estimate the impact of sentiment on price changes. We present a method and implementation that analyses the content of news using multiple dictionaries that accounts for the specific use of terminology in a given domain. To evaluate our approach we build different collections of domain related news for two financial markets and examine the impact that topical news has on two financial benchmarks in the equity and oil markets. We examine how the level of news sentiment from different news sources influences financial returns over time. We create a trading signal based on the news impact that predicts next day returns in the Dow Jones Industrial Average and West Texas Intermediate crude oil. We find that incorporating news sentiment into a trading strategy increases annual returns over a simple buy and hold strategy for both markets.