TheMachine Press

A daily newspaper for the age of artificial intelligence.

Morning editionPermanent story

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.

Published Updated Story ID: mp-2026-09-13-007
Read the complete editionStory JSON

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

  1. 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

  1. arXiv preprint 2609.11144arXiv · primary research

Corrections

No corrections have been recorded for this story.