Developing a Test Collection for the Evaluation of Integrated Search

作者: Marianne Lykke , Birger Larsen , Haakon Lund , Peter Ingwersen

DOI: 10.1007/978-3-642-12275-0_63

关键词: Search boxSet (abstract data type)MetadataDomain (software engineering)Computer scienceResult listInformation retrievalRelevance (information retrieval)Range (mathematics)Test (assessment)

摘要: The poster discusses the characteristics needed in an information retrieval (IR) test collection to facilitate evaluation of integrated search, i.e. search across a range different sources but with one box and ranked result list, describes analyses new constructed for this purpose. consists approx. 18,000 monographic records, 160,000 papers journal articles PDF 275,000 abstracts varied set metadata vocabularies from physics domain, 65 topics based on real work tasks corresponding graded relevance assessments. may be used systems- as well user-oriented evaluation.

参考文章(4)
Diane Kelly, Xin Fu, Eliciting better information need descriptions from users of information search systems Information Processing & Management. ,vol. 43, pp. 30- 46 ,(2007) , 10.1016/J.IPM.2006.03.006
Eero Sormunen, Liberal relevance criteria of TREC - Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '02. pp. 324- 330 ,(2002) , 10.1145/564376.564433
Kalervo Järvelin, An analysis of two approaches in information retrieval: From frameworks to study designs Journal of the Association for Information Science and Technology. ,vol. 58, pp. 971- 986 ,(2007) , 10.1002/ASI.V58:7
Kalervo Järvelin, An analysis of two approaches in information retrieval: From frameworks to study designs Journal of the American Society for Information Science and Technology. ,vol. 58, pp. 971- 986 ,(2007) , 10.1002/ASI.20589