{"id":"https://openalex.org/W1967193210","doi":"https://doi.org/10.1145/2699669","title":"Two-Stage Document Length Normalization for Information Retrieval","display_name":"Two-Stage Document Length Normalization for Information Retrieval","publication_year":2015,"publication_date":"2015-02-17","ids":{"openalex":"https://openalex.org/W1967193210","doi":"https://doi.org/10.1145/2699669","mag":"1967193210"},"language":"en","primary_location":{"id":"doi:10.1145/2699669","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2699669","pdf_url":null,"source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"},"type":"article","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/A5066848156","display_name":"Seung\u2010Hoon Na","orcid":"https://orcid.org/0000-0002-4372-7125"},"institutions":[{"id":"https://openalex.org/I83015752","display_name":"Busan University of Foreign Studies","ror":"https://ror.org/0455zdm83","country_code":"KR","type":"education","lineage":["https://openalex.org/I83015752"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Seung-Hoon Na","raw_affiliation_strings":["Busan University of Foreign Studies, South Korea"],"affiliations":[{"raw_affiliation_string":"Busan University of Foreign Studies, South Korea","institution_ids":["https://openalex.org/I83015752"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5066848156"],"corresponding_institution_ids":["https://openalex.org/I83015752"],"apc_list":null,"apc_paid":null,"fwci":4.7676,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.94891481,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"33","issue":"2","first_page":"1","last_page":"40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9987999796867371,"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":0.9987999796867371,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9980999827384949,"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/T10028","display_name":"Topic Modeling","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.8669565916061401},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7650465965270996},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.7353362441062927},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5697588920593262},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.43515291810035706},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39164677262306213}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8669565916061401},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7650465965270996},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.7353362441062927},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5697588920593262},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.43515291810035706},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39164677262306213},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"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":1,"locations":[{"id":"doi:10.1145/2699669","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2699669","pdf_url":null,"source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W136907812","https://openalex.org/W1482214997","https://openalex.org/W1487855083","https://openalex.org/W1517590677","https://openalex.org/W1549770780","https://openalex.org/W1568663196","https://openalex.org/W1577504169","https://openalex.org/W1605873790","https://openalex.org/W1763381236","https://openalex.org/W1966093341","https://openalex.org/W1969413882","https://openalex.org/W1973435495","https://openalex.org/W1985180788","https://openalex.org/W1990589796","https://openalex.org/W1995461500","https://openalex.org/W1999822363","https://openalex.org/W2000569744","https://openalex.org/W2004545875","https://openalex.org/W2005545412","https://openalex.org/W2009077327","https://openalex.org/W2014415866","https://openalex.org/W2015441003","https://openalex.org/W2019509999","https://openalex.org/W2026095310","https://openalex.org/W2029555656","https://openalex.org/W2031302834","https://openalex.org/W2032854262","https://openalex.org/W2040631151","https://openalex.org/W2046902062","https://openalex.org/W2046983134","https://openalex.org/W2058134741","https://openalex.org/W2061261643","https://openalex.org/W2070740689","https://openalex.org/W2071208361","https://openalex.org/W2074280490","https://openalex.org/W2082359527","https://openalex.org/W2086298942","https://openalex.org/W2087696423","https://openalex.org/W2098034778","https://openalex.org/W2104557041","https://openalex.org/W2105157020","https://openalex.org/W2107370612","https://openalex.org/W2119119231","https://openalex.org/W2124483996","https://openalex.org/W2134195052","https://openalex.org/W2134557008","https://openalex.org/W2136542423","https://openalex.org/W2142769902","https://openalex.org/W2148212498","https://openalex.org/W2149427297","https://openalex.org/W2152784831","https://openalex.org/W2155482025","https://openalex.org/W2155825896","https://openalex.org/W2162432120","https://openalex.org/W2162697159","https://openalex.org/W2203835818","https://openalex.org/W4234200495","https://openalex.org/W4240913316","https://openalex.org/W4252076394"],"related_works":["https://openalex.org/W4241523039","https://openalex.org/W178231042","https://openalex.org/W2360028903","https://openalex.org/W4280543773","https://openalex.org/W2366083136","https://openalex.org/W2387622493","https://openalex.org/W1932132538","https://openalex.org/W2357832196","https://openalex.org/W1566252468","https://openalex.org/W2591697403"],"abstract_inverted_index":{"The":[0],"standard":[1,50,142,158],"approach":[2,51],"for":[3],"term":[4,47,100],"frequency":[5,101],"normalization":[6,76,82],"is":[7,95,115],"based":[8],"only":[9],"on":[10,43,61,141],"the":[11,19,22,26,31,35,44,49,62,99,103,106,122,147],"document":[12,32,94],"length.":[13,33],"However,":[14],"it":[15],"does":[16],"not":[17],"distinguish":[18],"verbosity":[20,36,79,91,104,132],"from":[21,55],"scope,":[23],"these":[24,70],"being":[25],"two":[27],"main":[28],"factors":[29],"determining":[30],"Because":[34],"and":[37,80,84],"scope":[38,81,109],"have":[39],"largely":[40],"different":[41,87],"effects":[42],"increase":[45],"in":[46,117],"frequency,":[48],"can":[52],"easily":[53],"suffer":[54],"insufficient":[56],"or":[57],"excessive":[58],"penalization":[59,88],"depending":[60],"specific":[63],"type":[64],"of":[65,105],"long":[66],"document.":[67,107],"To":[68],"overcome":[69],"problems,":[71],"this":[72],"article":[73],"proposes":[74],"two-stage":[75],"by":[77,85,97,102],"performing":[78],"separately,":[83],"employing":[86],"functions.":[89],"In":[90,108],"normalization,":[92,110],"each":[93],"prenormalized":[96,123],"dividing":[98],"an":[111],"existing":[112],"retrieval":[113,135,159],"model":[114,149],"applied":[116],"a":[118],"straightforward":[119],"manner":[120],"to":[121,128,151],"document,":[124],"finally":[125],"leading":[126],"us":[127],"formulate":[129],"our":[130],"proposed":[131],"normalized":[133],"(VN)":[134],"model.":[136],"Experimental":[137],"results":[138],"carried":[139],"out":[140],"TREC":[143],"collections":[144],"demonstrate":[145],"that":[146],"VN":[148],"leads":[150],"marginal":[152],"but":[153],"statistically":[154],"significant":[155],"improvements":[156],"over":[157],"models.":[160]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}