Emotional and aesthetic highlights detection in movies

Affective computing is now an important research area of computer science with existing ties with the humanities as is demonstrated by the activities in text sentiment analysis and affective tagging of movies. We plan to emphasize and develop these links with the humanities and namely with film studies, concentrating on one of the most popular media: the movies. In this project, we test the degree of emotional participation of the audience in film watching. How do viewers react to the sequences in a given movie that film critics and filmmakers consider as aesthetically successful and therefore emotionally relevant?. This project therefore aims at answering the following computer science research questions: (1) How to determine the users’ affective state from multimodal signals, in the context of real movie projection? (2) Can the information carried out from the physiological and behavioural signals of multiple spectators be utilised to predict the emotional and aesthetic value of movie scenes (highlights)? (3) Can a multimodal synchronization / highlight detection system be used in film studies to determine movie scenes with high aesthetic value?

Guillaume Chanel
Head of the SIMS group

Developping user sensing