{"id":"https://openalex.org/W2015338694","doi":"https://doi.org/10.1145/1076034.1076064","title":"Information retrieval system evaluation","display_name":"Information retrieval system evaluation","publication_year":2005,"publication_date":"2005-08-15","ids":{"openalex":"https://openalex.org/W2015338694","doi":"https://doi.org/10.1145/1076034.1076064","mag":"2015338694"},"language":"en","primary_location":{"id":"doi:10.1145/1076034.1076064","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1076034.1076064","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072614956","display_name":"Mark Sanderson","orcid":"https://orcid.org/0000-0003-0487-9609"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mark Sanderson","raw_affiliation_strings":["University of Sheffield, Sheffield, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041495909","display_name":"Justin Zobel","orcid":"https://orcid.org/0000-0001-6622-032X"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Justin Zobel","raw_affiliation_strings":["RMIT, Melbourne, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RMIT, Melbourne, Australia","institution_ids":["https://openalex.org/I82951845"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":26.5397,"has_fulltext":false,"cited_by_count":369,"citation_normalized_percentile":{"value":0.99852941,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"162","last_page":"169"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/wilcoxon-signed-rank-test","display_name":"Wilcoxon signed-rank test","score":0.7824982404708862},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7263984680175781},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.7189854979515076},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6384573578834534},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.5867300629615784},{"id":"https://openalex.org/keywords/sign-test","display_name":"Sign test","score":0.5414109826087952},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5321853160858154},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5041860342025757},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.4691825211048126},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.41738373041152954},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.3632989525794983},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3240797519683838},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.30207735300064087},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14636382460594177},{"id":"https://openalex.org/keywords/mann\u2013whitney-u-test","display_name":"Mann\u2013Whitney U test","score":0.12973961234092712},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0745093822479248}],"concepts":[{"id":"https://openalex.org/C206041023","wikidata":"https://www.wikidata.org/wiki/Q1751970","display_name":"Wilcoxon signed-rank test","level":3,"score":0.7824982404708862},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7263984680175781},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.7189854979515076},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6384573578834534},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.5867300629615784},{"id":"https://openalex.org/C165793278","wikidata":"https://www.wikidata.org/wiki/Q2301904","display_name":"Sign test","level":4,"score":0.5414109826087952},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5321853160858154},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5041860342025757},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.4691825211048126},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41738373041152954},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.3632989525794983},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3240797519683838},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.30207735300064087},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14636382460594177},{"id":"https://openalex.org/C12868164","wikidata":"https://www.wikidata.org/wiki/Q1424533","display_name":"Mann\u2013Whitney U test","level":2,"score":0.12973961234092712},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0745093822479248},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1076034.1076064","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1076034.1076064","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:alma.61RMIT_INST:11246845730001341","is_oa":false,"landing_page_url":"http://doi.acm.org/10.1145/1076034.1076064","pdf_url":null,"source":{"id":"https://openalex.org/S4306402074","display_name":"RMIT Research Repository (RMIT University Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I82951845","host_organization_name":"RMIT University","host_organization_lineage":["https://openalex.org/I82951845"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:jupiter.its.unimelb.edu.au:11343/32016","is_oa":false,"landing_page_url":"http://hdl.handle.net/11343/32016","pdf_url":null,"source":{"id":"https://openalex.org/S4377196259","display_name":"Minerva Access (University of Melbourne)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I165779595","host_organization_name":"The University of Melbourne","host_organization_lineage":["https://openalex.org/I165779595"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SIGIR05: The 28th ACM/SIGIR International Symposium on Information Retrieval 2005","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6100000143051147,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W75771211","https://openalex.org/W354956471","https://openalex.org/W1507150160","https://openalex.org/W1985554184","https://openalex.org/W1987690005","https://openalex.org/W2015629112","https://openalex.org/W2047860186","https://openalex.org/W2073722401","https://openalex.org/W2075893676","https://openalex.org/W2077046902","https://openalex.org/W2109244020","https://openalex.org/W4211088184","https://openalex.org/W4233760227","https://openalex.org/W4237624558","https://openalex.org/W4251560691"],"related_works":["https://openalex.org/W1946812442","https://openalex.org/W584167426","https://openalex.org/W2014452851","https://openalex.org/W1981089293","https://openalex.org/W1599875686","https://openalex.org/W4205615042","https://openalex.org/W4281954079","https://openalex.org/W4386333995","https://openalex.org/W3193678936","https://openalex.org/W2030121706"],"abstract_inverted_index":{"The":[0],"effectiveness":[1,101],"of":[2,15,28,65,119,129],"information":[3],"retrieval":[4],"systems":[5],"is":[6,77,89],"measured":[7],"by":[8],"comparing":[9],"performance":[10],"on":[11,113],"a":[12,96],"common":[13],"set":[14],"queries":[16],"and":[17,88,134],"documents.":[18],"Significance":[19],"tests":[20,68,115],"are":[21],"often":[22],"used":[23],"to":[24,149],"evaluate":[25],"the":[26,52,63,75,83,117,127,145],"reliability":[27,128],"such":[29,35,67,120,151],"comparisons.":[30],"Previous":[31],"work":[32,44,112],"has":[33],"examined":[34],"tests,":[36],"but":[37,51],"produced":[38],"results":[39,107],"with":[40,166],"limited":[41],"application.":[42],"Other":[43],"established":[45],"an":[46],"alternative":[47],"benchmark":[48],"for":[49],"significance,":[50],"resulting":[53],"test":[54,164],"was":[55],"too":[56],"stringent.":[57],"In":[58],"this":[59],"paper,":[60],"we":[61],"revisit":[62],"question":[64],"how":[66],"should":[69],"be":[70,160],"used.":[71],"We":[72,122],"find":[73],"that":[74,109,139,156],"t-test":[76],"highly":[78],"reliable":[79,92],"(more":[80],"so":[81],"than":[82,93],"sign":[84],"or":[85],"Wilcoxon":[86],"test),":[87],"far":[90],"more":[91,167],"simply":[94],"showing":[95],"large":[97],"percentage":[98],"difference":[99],"in":[100,171],"measures":[102],"between":[103,126],"IR":[104],"systems.":[105],"Our":[106],"show":[108],"past":[110,140],"empirical":[111],"significance":[114],"over-estimated":[116],"error":[118],"tests.":[121],"also":[123],"re-consider":[124],"comparisons":[125,141],"precision":[130],"at":[131],"rank":[132],"10":[133],"mean":[135],"average":[136],"precision,":[137],"arguing":[138],"did":[142],"not":[143],"consider":[144],"assessor":[146,157],"effort":[147,158],"required":[148],"compute":[150],"measures.":[152],"This":[153],"investigation":[154],"shows":[155],"would":[159],"better":[161],"spent":[162],"building":[163],"collections":[165],"topics,":[168],"each":[169],"assessed":[170],"less":[172],"detail.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":25},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":15},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":17},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":21},{"year":2012,"cited_by_count":21}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2016-06-24T00:00:00"}