research
A Sentiment Score That Matched People Did Not Necessarily Rank Tomorrow
Five instruments on 70,500 messages separated semantic agreement from predictive ordering around securities lawsuits.
Summary
Five instruments on 70,500 messages separated semantic agreement from predictive ordering around securities lawsuits.
Researchers linked 70,500 X messages about securities class actions from 2002–2025 to abnormal returns, then ran VADER, Loughran–McDonald, FinBERT, Twitter-RoBERTa and an LLM annotator through one pipeline. Human-label agreement aligned more closely with graded same-day associations under conventional sampling, while a fixed-size panel produced similar graded rank correlations at same-day and one-day horizons. Coarse predictive ordering remained weak, and message volume predicted neither market damage nor settlement size in a corpus with 17.6% spam. This observational result is not trading guidance.
Why it matters
Five instruments on 70,500 messages separated semantic agreement from predictive ordering around securities lawsuits.
Limits and context
- This observational result is not trading guidance.
Key claims
Five instruments on 70,500 messages separated semantic agreement from predictive ordering around securities lawsuits.
Qualification: This observational result is not trading guidance.
Evidence: source-2026-09-13-007
Sources
- arXiv preprint 2609.11144arXiv · primary research
Corrections
No corrections have been recorded for this story.