{"id":"https://openalex.org/W2037022968","doi":"https://doi.org/10.1145/1099554.1099733","title":"Redundant documents and search effectiveness","display_name":"Redundant documents and search effectiveness","publication_year":2005,"publication_date":"2005-10-31","ids":{"openalex":"https://openalex.org/W2037022968","doi":"https://doi.org/10.1145/1099554.1099733","mag":"2037022968"},"language":"en","primary_location":{"id":"doi:10.1145/1099554.1099733","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1099554.1099733","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM international conference on Information and knowledge management","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/A5033381958","display_name":"Yaniv Bernstein","orcid":null},"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":"Yaniv Bernstein","raw_affiliation_strings":["RMIT University, Melbourne, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RMIT University, Melbourne, Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"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 University, Melbourne, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RMIT University, Melbourne, Australia","institution_ids":["https://openalex.org/I82951845"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I82951845"],"apc_list":null,"apc_paid":null,"fwci":4.6871,"has_fulltext":false,"cited_by_count":63,"citation_normalized_percentile":{"value":0.95750113,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"736","last_page":"743"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9968000054359436,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9968000054359436,"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"}},{"id":"https://openalex.org/T11492","display_name":"Academic integrity and plagiarism","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9959999918937683,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8379512429237366},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.8126308917999268},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.7145470976829529},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.6254173517227173},{"id":"https://openalex.org/keywords/terabyte","display_name":"Terabyte","score":0.6136194467544556},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5988749861717224},{"id":"https://openalex.org/keywords/equivalence","display_name":"Equivalence (formal languages)","score":0.5279936790466309},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.37217581272125244}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8379512429237366},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.8126308917999268},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.7145470976829529},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.6254173517227173},{"id":"https://openalex.org/C199683683","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Terabyte","level":2,"score":0.6136194467544556},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5988749861717224},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.5279936790466309},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.37217581272125244},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1099554.1099733","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1099554.1099733","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},{"id":"pmh:oai:jupiter.its.unimelb.edu.au:11343/29972","is_oa":false,"landing_page_url":"http://hdl.handle.net/11343/29972","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":"CIKM05: Conference on Information and Knowledge Management","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320972","display_name":"RMIT University","ror":"https://ror.org/04ttjf776"},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W60779023","https://openalex.org/W63837240","https://openalex.org/W1481997832","https://openalex.org/W1536700701","https://openalex.org/W1596691921","https://openalex.org/W1609518033","https://openalex.org/W1810577788","https://openalex.org/W1981825277","https://openalex.org/W1987690005","https://openalex.org/W2007842132","https://openalex.org/W2015338694","https://openalex.org/W2067432306","https://openalex.org/W2072284402","https://openalex.org/W2073722401","https://openalex.org/W2074449313","https://openalex.org/W2111295912","https://openalex.org/W2129070169","https://openalex.org/W2139532006","https://openalex.org/W2152565070","https://openalex.org/W2160484851","https://openalex.org/W2164634022","https://openalex.org/W2169189540","https://openalex.org/W2197919320","https://openalex.org/W2621280964","https://openalex.org/W2626151870","https://openalex.org/W2758584545","https://openalex.org/W3145042860","https://openalex.org/W4230624213","https://openalex.org/W4233760227","https://openalex.org/W4250366158","https://openalex.org/W4285719527","https://openalex.org/W6675220417"],"related_works":["https://openalex.org/W1976914335","https://openalex.org/W2066858118","https://openalex.org/W2134017072","https://openalex.org/W2915208987","https://openalex.org/W2381242807","https://openalex.org/W1940452713","https://openalex.org/W2152256925","https://openalex.org/W1994777790","https://openalex.org/W2751208925","https://openalex.org/W3126131230"],"abstract_inverted_index":{"The":[0,19],"web":[1],"contains":[2],"a":[3,82,87,105],"great":[4],"many":[5],"documents":[6,25,103,119],"that":[7,10,91,101,114],"are":[8],"content-equivalent,":[9],"is,":[11],"informationally":[12],"redundant":[13,24],"with":[14,51],"respect":[15],"to":[16,37,123],"each":[17],"other.":[18],"presence":[20],"of":[21,85,116],"such":[22],"mutually":[23],"in":[26,120],"search":[27,33,110],"results":[28],"can":[29],"degrade":[30],"the":[31,43,75,109,124],"user":[32,88],"experience.":[34],"Previous":[35],"attempts":[36],"address":[38],"this":[39,56],"issue,":[40],"most":[41],"notably":[42],"TREC":[44,76,125],"novelty":[45],"track,":[46],"were":[47,94,129],"characterized":[48],"by":[49],"difficulties":[50],"accuracy":[52],"and":[53,78],"evaluation.":[54],"In":[55],"paper":[57],"we":[58,112],"explore":[59],"syntactic":[60],"techniques":[61,73],"---":[62,66],"particularly":[63],"document":[64],"fingerprinting":[65],"for":[67],"detecting":[68],"content":[69],"equivalence.":[70],"Using":[71],"these":[72],"on":[74,108],"GOV1":[77],"GOV2":[79],"corpora":[80],"revealed":[81],"high":[83],"degree":[84],"redundancy;":[86],"study":[89],"confirmed":[90],"our":[92],"metrics":[93],"accurately":[95],"identifying":[96],"content-equivalence.":[97],"We":[98],"show,":[99],"moreover,":[100],"content-equivalent":[102],"have":[104],"significant":[106],"effect":[107],"experience:":[111],"found":[113],"16.6%":[115],"all":[117],"relevant":[118],"runs":[121],"submitted":[122],"2004":[126],"terabyte":[127],"track":[128],"redundant.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":5}],"updated_date":"2026-08-08T01:25:22.217667","created_date":"2025-10-10T00:00:00"}
