StockEmotions: Discover Investor Emotions for Financial Sentiment Analysis and Multivariate Time Series

Paper: arXiv 2301.09279

Authors: Jean Lee, Hoyoul Luis Youn, Josiah Poon, Soyeon Caren Han

Abstract

There has been growing interest in applying NLP techniques in the financial domain, however, resources are extremely limited. This paper introduces StockEmotions, a new dataset for detecting emotions in the stock market that consists of 10,000 English comments collected from StockTwits, a financial social media platform. Inspired by behavioral finance, it proposes 12 fine-grained emotion classes that span the roller coaster of investor emotion. Unlike existing financial sentiment datasets, StockEmotions presents granular features such as investor sentiment classes, fine-grained emotions, emojis, and time series data. To demonstrate the usability of the dataset, we perform a dataset analysis and conduct experimental downstream tasks. For financial sentiment/emotion classification tasks, DistilBERT outperforms other baselines, and for multivariate time series forecasting, a Temporal Attention LSTM model combining price index, text, and emotion features achieves the best performance than using a single feature.

Complexity vs Empirical Score

• Math Complexity: 3.5/10
• Empirical Rigor: 6.5/10
• Quadrant: Street Traders — practical and empirical, lighter on theory

Why this score: The paper introduces a novel, fine-grained 12-emotion dataset tailored for financial social media text, filling a notable gap in financial NLP. While the mathematical formulations are straightforward standard deep learning baselines (LSTM, DistilBERT), the empirical demonstration across classification and multivariate time series forecasting is solid and practical.

Research Flowchart

  flowchart TD
    A[Goal: Stock Market Emotion Detection & Time Series Forecasting] --> B[Dataset Creation: StockEmotions<br>10k StockTwits comments, 12 fine-grained emotion classes]
    B --> C[Integrated Inputs<br>Text, Emojis, Sentiment/Emotions, Stock Price Index]
    C --> D[Downstream Tasks & Modeling]
    D --> E[Task 1: Sentiment/Emotion Classification<br>Tested with DistilBERT]
    D --> F[Task 2: Multivariate Time Series Forecasting<br>Tested with Temporal Attention LSTM]
    E --> G[Outcome 1: DistilBERT achieves best classification performance]
    F --> H[Outcome 2: Combining price, text & emotion features yields best forecasting results]