{"id":"https://openalex.org/W1988711048","doi":"https://doi.org/10.1016/0306-4573(96)00008-8","title":"Document length normalization","display_name":"Document length normalization","publication_year":1996,"publication_date":"1996-09-01","ids":{"openalex":"https://openalex.org/W1988711048","doi":"https://doi.org/10.1016/0306-4573(96)00008-8","mag":"1988711048"},"language":"en","primary_location":{"id":"doi:10.1016/0306-4573(96)00008-8","is_oa":true,"landing_page_url":"https://doi.org/10.1016/0306-4573(96)00008-8","pdf_url":null,"source":{"id":"https://openalex.org/S174847851","display_name":"Information Processing & Management","issn_l":"0306-4573","issn":["0306-4573","1873-5371"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Processing & Management","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/0306-4573(96)00008-8","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086991902","display_name":"Amit Singhal","orcid":"https://orcid.org/0000-0002-4010-6614"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Amit Singhal","raw_affiliation_strings":["Department of Computer Science, 4130 Upson Hall, Cornell University, Ithaca, NY 14853-7501, U.S.A"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, 4130 Upson Hall, Cornell University, Ithaca, NY 14853-7501, U.S.A","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109936506","display_name":"Gerard Salton","orcid":null},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gerard Salton","raw_affiliation_strings":["Department of Computer Science, 4130 Upson Hall, Cornell University, Ithaca, NY 14853-7501, U.S.A"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, 4130 Upson Hall, Cornell University, Ithaca, NY 14853-7501, U.S.A","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052357764","display_name":"Mandar Mitra","orcid":"https://orcid.org/0009-0007-8026-3220"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mandar Mitra","raw_affiliation_strings":["Department of Computer Science, 4130 Upson Hall, Cornell University, Ithaca, NY 14853-7501, U.S.A"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, 4130 Upson Hall, Cornell University, Ithaca, NY 14853-7501, U.S.A","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003816022","display_name":"Chris Buckley","orcid":"https://orcid.org/0000-0002-5059-1668"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chris Buckley","raw_affiliation_strings":["Department of Computer Science, 4130 Upson Hall, Cornell University, Ithaca, NY 14853-7501, U.S.A"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, 4130 Upson Hall, Cornell University, Ithaca, NY 14853-7501, U.S.A","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5086991902"],"corresponding_institution_ids":["https://openalex.org/I205783295"],"apc_list":{"value":3220,"currency":"USD","value_usd":3220},"apc_paid":{"value":3220,"currency":"USD","value_usd":3220},"fwci":6.4788,"has_fulltext":false,"cited_by_count":201,"citation_normalized_percentile":{"value":0.96684401,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"32","issue":"5","first_page":"619","last_page":"633"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9990000128746033,"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":0.9975000023841858,"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":0.8000046014785767},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7098946571350098},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6421738862991333},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.6076877117156982},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.5614956617355347},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.4905764162540436},{"id":"https://openalex.org/keywords/trigonometric-functions","display_name":"Trigonometric functions","score":0.48311686515808105},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2331382930278778}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8000046014785767},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7098946571350098},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6421738862991333},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6076877117156982},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.5614956617355347},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.4905764162540436},{"id":"https://openalex.org/C178009071","wikidata":"https://www.wikidata.org/wiki/Q93344","display_name":"Trigonometric functions","level":2,"score":0.48311686515808105},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2331382930278778},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1016/0306-4573(96)00008-8","is_oa":true,"landing_page_url":"https://doi.org/10.1016/0306-4573(96)00008-8","pdf_url":null,"source":{"id":"https://openalex.org/S174847851","display_name":"Information Processing & Management","issn_l":"0306-4573","issn":["0306-4573","1873-5371"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Processing & Management","raw_type":"journal-article"},{"id":"pmh:oai:ecommons.cornell.edu:1813/7186","is_oa":false,"landing_page_url":"https://hdl.handle.net/1813/7186","pdf_url":null,"source":{"id":"https://openalex.org/S4306400757","display_name":"eCommons (Cornell University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"technical report"}],"best_oa_location":{"id":"doi:10.1016/0306-4573(96)00008-8","is_oa":true,"landing_page_url":"https://doi.org/10.1016/0306-4573(96)00008-8","pdf_url":null,"source":{"id":"https://openalex.org/S174847851","display_name":"Information Processing & Management","issn_l":"0306-4573","issn":["0306-4573","1873-5371"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Processing & Management","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W31450109","https://openalex.org/W1482214997","https://openalex.org/W1518529582","https://openalex.org/W1523298050","https://openalex.org/W1525341925","https://openalex.org/W1557757161","https://openalex.org/W1586089921","https://openalex.org/W1765388594","https://openalex.org/W1833785989","https://openalex.org/W1956559956","https://openalex.org/W1978394996","https://openalex.org/W2014415866","https://openalex.org/W2019509999","https://openalex.org/W2019976352","https://openalex.org/W2043909051","https://openalex.org/W2058089741","https://openalex.org/W2064579132","https://openalex.org/W2094788550","https://openalex.org/W2175529804","https://openalex.org/W2325227998","https://openalex.org/W2887107689","https://openalex.org/W4244833938","https://openalex.org/W6628905179","https://openalex.org/W6630783858","https://openalex.org/W6631142929","https://openalex.org/W6631459773","https://openalex.org/W6635057843","https://openalex.org/W6637871545","https://openalex.org/W6654076248","https://openalex.org/W6655391330","https://openalex.org/W6666477347","https://openalex.org/W6674168459","https://openalex.org/W6685271946","https://openalex.org/W6753469269"],"related_works":["https://openalex.org/W3028990185","https://openalex.org/W1869615134","https://openalex.org/W2154282042","https://openalex.org/W2114279702","https://openalex.org/W3200612347","https://openalex.org/W2104432161","https://openalex.org/W3114320778","https://openalex.org/W1579794579","https://openalex.org/W2462299551","https://openalex.org/W2021285090"],"abstract_inverted_index":{"In":[0],"the":[1,16,29,40,74,83],"TREC":[2],"collection\u2014a":[3],"large":[4],"full-text":[5],"experimental":[6],"text":[7],"collection":[8],"with":[9,28,50],"widely":[10],"varying":[11],"document":[12,20,30],"lengths\u2014we":[13],"observe":[14],"that":[15,34,44,90],"likelihood":[17,75,84],"of":[18,47,76,79,85],"a":[19,25,35,62,66],"being":[21],"judged":[22],"relevant":[23],"by":[24],"user":[26],"increases":[27],"length.":[31],"We":[32,64],"show":[33,89],"retrieval":[36,97],"strategy,":[37],"such":[38,61],"as":[39],"vector-space":[41],"cosine":[42,69],"match,":[43],"retrieves":[45],"documents":[46,59,78],"different":[48],"lengths":[49,81],"roughly":[51],"equal":[52],"chances,":[53],"will":[54],"not":[55],"optimally":[56],"retrieve":[57],"useful":[58],"from":[60],"collection.":[63],"present":[65],"modified":[67],"technique\u2014pivoted":[68],"normalization\u2014that":[70],"attempts":[71],"to":[72,82],"match":[73],"retrieving":[77],"all":[80],"their":[86],"relevance,":[87],"and":[88],"this":[91],"technique":[92],"yields":[93],"significant":[94],"improvements":[95],"in":[96],"effectiveness.":[98]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":9}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}