This study suggests evaluation criteria for the web-based question-answer databases provided by major Korean search portals. In particular, this study suggests evaluation criteria for the relevance of question titles, entire questions, and answers. The evaluation criteria for the quality of answers are also developed. Based on these criteria, evaluation of documents from Naver Knowledge-in are performed. The results of this study can be implemented to the development of test collection of question-answer databases. The implications for system designers and web content providers are discussed.
(2004) Invisible Web 탐색도구의 성능 비교 및 분석,
(1999) 정보 검색 시스템 평가를 위한 균형 테스트 컬렉션 구축,
(2005) 국내 웹 이용자의 검색 행태 추이 분석,
(2004) 지식검색서비스 이용에 관한 실증적 연구,
(2003) 웹 검색엔진의 지식검색커뮤니티 기반 지식관리에 관한 연구,
(2005) 문서구조를 이용한 질의응답문서 클러스터링에 관한 연구,
(2001) Expert searvices on the Web the commercial competi- tion for libraries,
(1964) On relevance as a mea- sure,
(1964) “The Notion of Rele- vance,
(2001) Ask- an-expert services analysis,
(1999) Authoritative sources in hyperlinked environment,
(2006) NHN: The little search engine that could,
(1959) National Academy of Sciences Procee- dings of the Internatioal Conference on Science Information National Academy of Sciences,
(2000) Human search engines: the next killer app,
(1975) A review of and a framework for the thinking on the notion in information science Journal of the American Society for Information Science,
(1997) Data quality in context,
(2005) Document quality models for web ad hoc retrie- val,
(2000) Incorporating quality metrics in centralized/ distri- buted information retrieval on the world wide web,