Fast Numbers, Slow Language: Bridging Quantitative and Qualitative Earnings Signals
2026-06-29 • Computation and Language
Computation and LanguageComputational Engineering, Finance, and Science
AI summaryⓘ
The authors studied how earnings announcements give two types of information: first, quick numbers compared to expectations that traders react to immediately, and later, the management's tone and explanations from conference calls that take longer to interpret. They noticed that finance experts and language researchers had different ways to study these signals, which made it hard to compare results. By creating a new dataset combining news, transcripts, and stock prices, the authors showed that numerical surprises affect stock prices quickly, while language signals influence prices the next day. This approach helps unite the two research areas for better understanding of market reactions.
earnings announcementsquantitative surpriseearnings conference call transcriptnatural language processingstock returnintraday pricessentiment analysismarket reactiontrading strategiesvolatility
Authors
Ding Yu, Zhuo Liu, Hao Zhang, Hangfeng He
Abstract
Earnings announcements release two types of information sequentially: quantitative surprise (numeric earnings-per-share (EPS)/revenue versus analyst estimate) arrives first in press releases and financial news, processed by algorithmic traders within minutes; qualitative language (management tone, guidance, question-and-answer (Q&A) credibility) arrives 30-90 min later in the earnings conference call transcript (ECT), requiring human interpretation overnight. Financial economists have studied quantitative surprise for 50 years; natural language processing (NLP) researchers have studied qualitative ECT signals for a decade. Despite studying the same event, the two communities used incompatible frameworks: different targets (return vs. volatility), trading setups (long top-decile and short bottom-decile vs. trade-all), and metrics (return spread between top and bottom 20% (Q5-Q1) vs. mean squared error (MSE)), making direct comparison and connection challenging. We bridge these communities with EarningsInOne, the first corpus aligning earnings news, ECTs, and intraday and next-day prices across SP 1500 (broad U.S. equity universe, 2022-2025). Applying unified trading and evaluation tools to both signal types, we confirm a clean speed separation, fast numbers, slow language: quantitative surprise peaks at announcement and is largely eliminated by the next market open; qualitative ECT sentiment peaks on the next trading day, real and tradeable, but hidden under prior transcript-based evaluation that optimised sign-agnostic volatility with pointwise MSE.