EmTract: Extracting Emotions from Social Media

Abstract

We develop an open-source tool (EmTract) that extracts emotions from social media text tailed for financial context. To do so, we annotate ten thousand short messages from a financial social media platform (StockTwits) and combine it with open-source emotion data. We then use a pre-tuned NLP model, DistilBERT, augment its embedding space by including 4,861 tokens (emojis and emoticons), and then fit it first on the open-source emotion data, then transfer it to our annotated financial social media data. Our model outperforms competing open-source state-of-the-art emotion classifiers, such as Emotion English DistilRoBERTa-base on both human and chatGPT annotated data. Compared to dictionary based methods, our methodology has three main advantages for research in finance. First, our model is tailored to financial social media text; second, it incorporates key aspects of social media data, such as non-standard phrases, emojis, and emoticons; and third, it operates by sequentially learning a latent representation that includes features such as word order, word usage, and local context. Using EmTract, we explore the relationship between investor emotions expressed on social media and asset prices. We show that firm-specific investor emotions are predictive of daily price movements. Our findings show that emotions and market dynamics are closely related, and we provide a tool to help study the role emotions play in financial markets.