Collaborative filtering with facial expressions for online video recommendation |
| |
| Institution: | 1. School of Dance & Culture Item Factory Center, Kyung Hee University, 1 Hoegi-dong, Dongdaemun-gu, Seoul 130-701, Republic of Korea;2. Department of E-business, College of Business Administration, Kyung Hee University, 1 Hoegi-dong, Dongdaemun-gu, Seoul 130-701, Republic of Korea;3. Jindal School of Management, University of Texas at Dallas, Richardson, TX 75080, United States;1. King Abdulaziz University, Faculty of Economics and Administration, Jeddah 21589, Saudi Arabia;2. HEC Montreal, Marketing Department 3000 Côte Sainte-Catherine, Montreal, QC H3T 2A7, Canada;1. Instituto de Ingeniería de Alimentos para el Desarrollo, Departamento de Tecnología de Alimentos, Universidad Politécnica de Valencia, Camino de Vera, s/n, 46022 Valencia, Spain;2. Laboratorio de Estudios Métricos de Información (LEMI), Departamento de Bibliotecomía y Documentación, Universidad Carlos III, Avenida de la Universidad, 30, 28911 Leganes, Madrid, Spain;3. Instituo de Gestión de la Información y del Conocimiento (CSIC—Universidad Politécnica de Valencia), UISYS (Universidad de Valencia), Plaza Cisneros, 4, 46003 Valencia, Spain;1. Research Centre of the Centre Hospitalier Universitaire de Québec, 10 rue de l''Espinay, Quebec City, QC G1L 3L5, Canada;2. Faculty of Nursing Sciences, Université Laval, QC, Canada;3. Research Centre on primary health care and services of Université Laval (CERSSPL-UL), CSSS de la Vieille-Capitale, 880 rue Père-Marquette, 3e étage, Québec City, QC G1S 2A4, Canada;4. Department of Political Science, Université Laval, Pavillon Charles-De Koninck, office 4453, Cité Universitaire, QC G1V 0A6, Canada;5. Department of Psychoeducation, Université du Québec à Trois-Rivières (UQTR), QC, Canada;1. College of Information Technology, Department of Information Systems, University Tenaga Nasional, Selangor, Malaysia;2. Department of Aviation & Supply Chain Management, Raymond J. Harbert College of Business, Auburn University, Auburn, AL 36849, USA;3. Department of Information System, University Putra Malaysia (UPM), 43300 Serdang, Selangor, Malaysia;4. Azad University, Tehran, Iran;5. University of Science and Culture, Tehran, Iran |
| |
| Abstract: | Online video recommender systems help users find videos suitable for their preferences. However, they have difficulty in identifying dynamic user preferences. In this study, we propose a new recommendation procedure using changes of users’ facial expressions captured every moment. Facial expressions portray the users’ actual emotions about videos. We can utilize them to discover dynamic user preferences. Further, because the proposed procedure does not rely on historical rating or purchase records, it properly addresses the new user problem, that is, the difficulty in recommending products to users whose past rating or purchase records are not available. To validate the recommendation procedure, we conducted experiments with footwear commercial videos. Experiment results show that the proposed procedure outperforms benchmark systems including a random recommendation, an average rating approach, and a typical collaborative filtering approach for recommendation to both new and existing users. From the results, we conclude that facial expressions are a viable element in recommendation. |
| |
| Keywords: | Online video recommender system Facial expression Personalization Collaborative filtering |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
