Sharing emotions: determining films’ evoked emotional experience from their online reviews

• Published in: Information retrieval (Boston) 2020-10, Vol.23 (5), p.475-501
• Main Authors: Mokryn, Osnat, Bodoff, David, Bader, Nadim, Albo, Yael, Lanir, Joel
• Format: Article
• Language: English
• Subjects: Computer Science; Data Mining and Knowledge Discovery; Data Structures and Information Theory; Decision making; Emotional factors; Emotions; Information Storage and Retrieval; Mining Actionable Insights from Online User Generated Content; Motion pictures; Multimedia; Natural Language Processing (NLP); Pattern Recognition; Recommender systems
• ISSN: 1386-4564; 1573-7659
• DOI: 10.1007/s10791-020-09373-1

Online reviews are broadly believed to reflect consumers’ opinions towards the reviewed items. In this work, we postulate that online reviews for experience goods also reflect something very different, the reviewer’s emotions while experiencing the item. We study the case of films, which are made with the intent of evoking an emotional response. We postulate that the emotions that the viewer experienced while watching the movie are reflected in their online review, and can be reliably extracted from it. We aggregate these emotional experiences to create an emotional signature for the film—the emotions that it tends to evoke in viewers. We conduct a series of validations, each designed to offer evidence that the emotional signature indeed reflects the emotions that the film evokes in viewers. Our results demonstrate that experience goods’ online reviews can be utilized for extracting and understanding users’ emotional experience. Items’ induced emotions can be used in affective recommender systems and affective multimedia retrieval. In addition, users’ ability to easily see in advance the emotions that the item has induced in others, is relevant for research on the effect of expected emotions on decision-making.