Source: Blankespoor, Ng, Ji & Zhao (2025) — “Incongruent CEO Facial Expressions and Analyst Forecast Dispersion”
At first this sounds like a technical finance question. Then you look closer and realise it is also a question about attention, incentives, and whether people are using information or just being impressed by it.
There’s a lot of communication happening in corporate earnings interviews that never makes it into the transcript. The research question this paper asks: do CEO facial expressions during interviews near earnings announcements affect how analysts process information? The mechanism they focus on is incongruence — specifically, the mismatch between what a CEO’s face is expressing and what the financial news actually is. A CEO who looks positive while delivering bad earnings news. Or a CEO who looks negative while reporting a strong quarter. These incongruent signals create a specific problem for the analyst trying to form an accurate picture. Using deep-learning based facial analysis applied to video recordings of CEO interviews, the researchers identify and score emotional expressions. They then compare these expressions to the concurrent earnings news. When the signals are incongruent — face and fundamentals pointing in different directions — analyst forecast dispersion increases afterwards. Analysts disagree more about the firm’s future. The effect is stronger when analysts are likely to have watched the interview and when they have fewer alternative information sources. There are two plausible interpretations.
In plain English, that is why the result matters beyond the chart. It changes where people should look, what they should question, and which comfortable assumption probably needs to be retired.
So I would not read this as a neat technology story. It is a messy information story. The tools improve, but people still have to decide what deserves attention. Annoying, but true.