Sentiment analysis and machine learning in finance: a comparison of methods and models on one million messages

• DOI: 10.1007/s42521-019-00014-x
• Publication Date: 2019-09-18T07:02:46Z
• Authors: Thomas Renault
• Keywords: JEL: G - Financial Economics/G.G1 - General Financial Markets/G.G1.G10 - General; 330; [QFIN]Quantitative Finance [q-fin]; 05 social sciences; Asset pricing; [QFIN] Quantitative Finance [q-fin]; JEL: G - Financial Economics/G.G1 - General Financial Markets/G.G1.G14 - Information and Market Efficiency • Event Studies • Insider Trading; Social media; Sentiment analysis; Machine learning; 0502 economics and business; JEL: G - Financial Economics/G.G1 - General Financial Markets/G.G1.G12 - Asset Pricing • Trading Volume • Bond Interest Rates; StockTwits

We use a large dataset of one million messages sent on the microblogging platform StockTwits to evaluate the performance of a wide range of preprocessing methods and machine learning algorithms for sentiment analysis in finance. We find that adding bigrams and emojis significantly improve sentiment classification performance. However, more complex and time-consuming machine learning methods, such as random forests or neural networks, do not improve the accuracy of the classification. We also provide empirical evidence that the preprocessing method and the size of the dataset have a strong impact on the correlation between investor sentiment and stock returns. While investor sentiment and stock returns are highly correlated, we do not find that investor sentiment derived from messages sent on social media helps in predicting large capitalization stocks return at a daily frequency.