Please CLICK HERE to download the presentation.
|Yasufumi Takama received the B. S. Degree, M.S. Degree, and Dr. Eng. Degree from University of Tokyo in 1994, 1996, and 1999, respectively. He was a JSPS (Japan Society for the Promotion of Science) Research Fellow from 1997 to 1999. From 1999 to 2002 he was a Research Associate at Tokyo Institute of Technology in Japan. From 2002 to 2005, he was an Associate Professor at Tokyo Metropolitan Institute of Technology, Japan. From 2005 to 2013, he was an Associate Professor at Tokyo Metropolitan University, Japan. Since 2014, he has been a Professor at Tokyo Metropolitan University, Japan. He also participated in PREST (Precursory Research for Embryonic Science and Technology), JST (Japan Science and Technology Corporation) from 2000 to 2003. His current research interest includes information recommendation, information visualization, data mining, and Web intelligence. Dr. Takama is a member of IEEE and ACM.|
Modeling Personal Values for Recommender Systems
Recommender systems are widely used in various applications, such as movie recommendations, e-commerce, and tourism. While traditional recommendation algorithms focus on estimating users’ preference from their past behaviors, we should consider other factors than preference to extend the scope of application, such as the recommendation for behavioral change. I think the personal values of users’ are one of such additional factors that should be taken into account by recommender systems. In this talk, I will introduce the method for modeling users’ personal values and how to incorporate them into recommender systems.