A Study on Personalized Recommendation Method Based on Contents Using Activity and Location Information
Yong Kim, Mun-Seok Kim, Yoon-Beom Kim, Jaehong Park · Journal of the Korean Society for information Management · 2009
ABSTRACT In this paper, we propose user contents using behavior and loca tion information on contents on various channels, such as web, IPTV, for contents distributi on. With methods to build user and contents profiles, contents using behavior as an implicit user feedback was applied into machine learning procedure for updating user profiles and contents preference. In machine learning procedure, contents-based and collaborative filtering methods were used to analyze user's contents preference. This study proposes contents locati on information on web sites for final recommendation contents as well. Finally, we refer to a g eneralized recommender system for personalization. With those methods, more effective and acc urate recommendation service can be possible. 키워드 : 개인화 , 추천 , 협업여과추천 , 내용기반추천 IPTV, personalization, recommendation, collaborative filtering, contents-based recommendation ********** 전북대학교 문헌정보학과 조교수([email protected]) ( 제1저자)전라북도 교육청 기록관리사([email protected]) ( 공동저자)전북대학교 문헌정보학과 석사과정([email protected]) ( 공동저자)(주) 유라클 대표이사([email protected]) ( 공동저자)