ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술대회 Multi-View Topic Model Learning to Generate Audience Metadata Automatically
Cited 0 time in scopus Download 1 time Share share facebook twitter linkedin kakaostory
저자
박원주, 손정우, 이상윤, 김선중
발행일
201801
출처
International Conference on Information Networking (ICOIN) 2018, pp.562-564
DOI
https://dx.doi.org/10.1109/ICOIN.2018.8343181
협약과제
17HR2700, 개방형 미디어 생태계 구축을 위한 시맨틱 클러스터 기반 시청상황 적응형 스마트방송 기술 개발, 김선중
초록
In this paper, we propose a study on multi-view topic model learning to generate automatically audience metadata for clips. We use closed caption of broadcasting contents, user's subscription information and viewing history. An existing topic model has limits to being utilized for user targeted services by learning topics based on subtitles or scripts without user data. To overcome this limitation, this paper proposes a multi-view topic model learning technique using multi domain data such as closed caption of broadcast contents and viewing rating of audience groups.
KSP 제안 키워드
Broadcasting contents, Closed caption, Model learning, Multi-view, Subscription information, User data, topic model