Event-Aware Sentiment Factors from LLM-Augmented Financial Tweets: A Transparent Framework for Interpretable Quant Trading

TL;DR

This paper demonstrates how large language models can be used to extract interpretable, multi-label event signals from financial tweets, which can inform trading strategies with statistically significant alpha signals.

Contribution

It introduces a transparent, reproducible framework for converting social media text into structured event variables for financial prediction using LLMs.

Findings

Certain event labels yield negative alpha signals

Sharpe ratios as low as -0.38 for some signals

Information coefficients exceed 0.05, statistically significant

Abstract

In this study, we wish to showcase the unique utility of large language models (LLMs) in financial semantic annotation and alpha signal discovery. Leveraging a corpus of company-related tweets, we use an LLM to automatically assign multi-label event categories to high-sentiment-intensity tweets. We align these labeled sentiment signals with forward returns over 1-to-7-day horizons to evaluate their statistical efficacy and market tradability. Our experiments reveal that certain event labels consistently yield negative alpha, with Sharpe ratios as low as -0.38 and information coefficients exceeding 0.05, all statistically significant at the 95\% confidence level. This study establishes the feasibility of transforming unstructured social media text into structured, multi-label event variables. A key contribution of this work is its commitment to transparency and reproducibility; all code and methodologies are made publicly available. Our results provide compelling evidence that social media sentiment is a valuable, albeit noisy, signal in financial forecasting and underscore the potential of open-source frameworks to democratize algorithmic trading research.