Which Voices Move Markets? Speaker Identity and the Cross-Section of Post-Earnings Returns

TL;DR

This study uses a domain-specific transformer model to analyze earnings call transcripts, revealing that different speakers influence stock returns differently and that sentiment signals can predict market movements.

Contribution

It introduces a novel speaker-weighted sentiment measure using FinBERT, demonstrating its effectiveness in predicting post-earnings stock returns beyond traditional methods.

Findings

Speaker sentiment significantly predicts stock returns.

FinBERT-based sentiment outperforms traditional dictionary approaches.

Results are validated with rigorous out-of-sample tests.

Abstract

We utilize FinBERT, a domain-specific transformer model, to parse 6.5 million sentences from 16,428 S&P 500 quarterly earnings call transcripts (2015-2025) and demonstrate that post-earnings stock returns are not equally affected by all speakers in a conference call. Our section-weighted sentiment, with empirically derived speaker weights (Analyst 49%, CFO 30%, Executive 16%, Other 5%), achieves an out-of-sample Spearman IC of 0.142 versus 0.115 in-sample, generates monthly long-short alpha of 2.03% unexplained by the Fama-French five-factor model (t = 6.49), and remains significant after controlling for standardized unexpected earnings (SUE). FinBERT section-weighted sentiment entirely subsumes the Loughran-McDonald dictionary approach (FinBERT t = 5.90; LM t = 0.86 in the combined specification). Signal decay analysis and cumulative abnormal return charts confirm gradual price adjustment consistent with sluggish assimilation of soft information. All results undergo rigorous out-of-sample validation with an explicit temporal split, yielding improved rather than deteriorated predictive power.