Source: Obaid & Pukthuanthong (2022) — “A Picture Is Worth a Thousand Words: Measuring Investor Sentiment by Combining Machine Learning and Photos from News”
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.
Investor sentiment research has traditionally relied on textual signals: analyst tone, social media commentary, survey responses, word counts in financial news. This paper explores a different channel — the visual content of news photographs — and finds it contains information that text doesn’t capture. News articles are accompanied by photos that convey emotional tone visually. An article about financial markets accompanied by a photo of a stressed trader on a chaotic trading floor communicates something different from the same article next to a photo of calm offices and confident executives. These visual cues affect how readers process information, and they may reflect editorial judgments about sentiment that differ from what the text explicitly states. The researchers use machine learning to classify news photos on a pessimism dimension and construct a daily Photo Pessimism index from a large sample of news images. Consistent with behavioural finance predictions, Photo Pessimism predicts market return reversals — periods of high photo-based pessimism are followed by positive returns as the sentiment overshoots and corrects.
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.