---
title: Extracting the Structure of Press Releases for Predicting Earnings Announcement Returns
url: https://www.ml-quant.com/papers/doi/10-1145-3768292-3770344/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-09-26
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
identifier: doi:10.1145/3768292.3770344
source_url: http://dx.doi.org/10.1145/3768292.3770344
featured: 2025-10-03
citations: 0
topic: LLMs & Text
---


# Extracting the Structure of Press Releases for Predicting Earnings Announcement Returns

The research explores the predictive power of textual features in earnings press releases on stock returns, concluding that press release content is as informative as earnings surprise, with FinBERT being the most predictive.

- Source: http://dx.doi.org/10.1145/3768292.3770344
- Identifier: doi:10.1145/3768292.3770344
- Released: 2025-09-29
- First featured: Quant Letter No. 114 (2025-10-03): https://www.ml-quant.com/issues/2025-10-03/
- Citations (Semantic Scholar): 0
- Published in: Proceedings of the 6th ACM International Conference on AI in Finance
- Topic: LLMs & Text

## Related

- [Advanced Deep Learning Techniques for Analyzing Earnings Call Transcripts: Methodologies and Applications](https://www.ml-quant.com/papers/arxiv/2503.01886/): The paper compares the effectiveness of deep learning methods like BERT, FinBERT, and ULMFiT in sentiment analysis of financial transcripts, offering insights for practical financial decision-making.
- [Planning In Natural Language Improves LLM Search For Code Generation](https://www.ml-quant.com/papers/arxiv/2409.03733/): PLANSEARCH is a new search algorithm that creates diverse solutions for natural language problems, outperforming traditional methods in various benchmarks.
- [Fine-Tuning and Prompt Optimization: Two Great Steps that Work Better Together](https://www.ml-quant.com/papers/arxiv/2407.10930/): The article explores a method to enhance Natural Language Processing systems by simultaneously optimizing language model weights and prompting strategies, leading to significant improvements in tasks like multi-hop QA and mathematical reasoning.
- [The (Short-Term) Effects of Large Language Models on Unemployment and Earnings](https://www.ml-quant.com/papers/arxiv/2509.15510/): Large Language Models like ChatGPT have boosted earnings for workers in certain occupations without affecting unemployment rates, indicating they enhance income rather than replace jobs.
- [Visualizing Public Opinion on X: A Real-Time Sentiment Dashboard Using VADER and DistilBERT](https://www.ml-quant.com/papers/arxiv/2504.15448/): A sentiment analysis system, using Natural Language Processing and machine learning, offers real-time interpretation of public opinion towards corporations, highlighting disparities in public sentiment and assisting stakeholders in strategic decision-making.
- [The News in Earnings Announcement Disclosures: Capturing Word Context Using LLM Methods](https://www.ml-quant.com/papers/ssrn/5198675/): The paper reveals that textual disclosures in companies' earnings announcements, analyzed through a large language model, account for a significant portion of stock return variations and immediate price revisions.