A picture is worth a thousand words: Measuring investor sentiment by combining machine learning and photos from news

• 成果类型: Article
• 署名作者: Obaid, Khaled; Pukthuanthong, Kuntara
• 署名单位: California State University System; California State University East Bay; University of Missouri System; University of Missouri Columbia
• 刊物名称: JOURNAL OF FINANCIAL ECONOMICS
• ISSN/ISSBN: 0304-405X
• DOI: 10.1016/j.jfineco.2021.06.002
• 发表日期: 2022
• 页码: 273-297
• 关键词: Investor sentiment; behavioral finance; Return predictability; Machine Learning; Deep learning; big data

摘要

By applying machine learning to the accurate and cost-effective classification of photos based on sentiment, we introduce a daily market-level investor sentiment index (Photo Pessimism) obtained from a large sample of news photos. Consistent with behavioral mod -els, Photo Pessimism predicts market return reversals and trading volume. The relation is strongest among stocks with high limits to arbitrage and during periods of elevated fear. We examine whether Photo Pessimism and pessimism embedded in news text act as com-plements or substitutes for each other in predicting stock returns and find evidence that the two are substitutes. Published by Elsevier B.V.