# Investor Emotions and Earnings Announcements

arXiv: https://arxiv.org/abs/2006.13934 · HTML: https://mlsanity.com/paper/2006.13934/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jun 2020.

## Built on by (most cited first, 4 of 4)

- [EmTract: Extracting Emotions from Social Media](https://mlsanity.com/paper/2112.03868/) (2021)
- [Model-Free Reinforcement Learning for Asset Allocation](https://mlsanity.com/paper/2209.10458/) (2022)
- [Quantifying A Firm's AI Engagement: Constructing Objective, Data-Driven, AI Stock Indices Using 10-K Filings](https://mlsanity.com/paper/2501.01763/) (2025)
- [FinMoji: A Framework for Emoji-driven Sentiment Analysis in Financial Social Media](https://mlsanity.com/paper/2605.09469/) (2026)

## Abstract (arXiv)

Armed with a decade of social media data, I explore the impact of investor emotions on earnings announcements. In particular, I test whether the emotional content of firm-specific messages posted on social media just prior to a firm's earnings announcement predicts its earnings and announcement returns. I find that investors are typically excited about firms that end up exceeding expectations, yet their enthusiasm results in lower announcement returns. Specifically, a standard deviation increase in excitement is associated with an 7.8 basis points lower announcement return, which translates into an approximately -5.8% annualized loss. My findings confirm that emotions and market dynamics are closely related and highlight the importance of considering investor emotions when assessing a firm's short-term value.