{"id":"https://openalex.org/W2114651011","doi":"https://doi.org/10.1145/2652524.2652556","title":"A replicated study on duplicate detection","display_name":"A replicated study on duplicate detection","publication_year":2014,"publication_date":"2014-09-05","ids":{"openalex":"https://openalex.org/W2114651011","doi":"https://doi.org/10.1145/2652524.2652556","mag":"2114651011"},"language":"en","primary_location":{"id":"doi:10.1145/2652524.2652556","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2652524.2652556","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://lup.lub.lu.se/record/4647034","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004374106","display_name":"Markus Borg","orcid":"https://orcid.org/0000-0001-7879-4371"},"institutions":[{"id":"https://openalex.org/I187531555","display_name":"Lund University","ror":"https://ror.org/012a77v79","country_code":"SE","type":"education","lineage":["https://openalex.org/I187531555"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Markus Borg","raw_affiliation_strings":["Lund University, Sweden","Lund Univ., Sweden#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lund University, Sweden","institution_ids":["https://openalex.org/I187531555"]},{"raw_affiliation_string":"Lund Univ., Sweden#TAB#","institution_ids":["https://openalex.org/I187531555"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087032437","display_name":"Per Runeson","orcid":"https://orcid.org/0000-0003-2795-4851"},"institutions":[{"id":"https://openalex.org/I187531555","display_name":"Lund University","ror":"https://ror.org/012a77v79","country_code":"SE","type":"education","lineage":["https://openalex.org/I187531555"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Per Runeson","raw_affiliation_strings":["Lund University, Sweden","Lund Univ., Sweden#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lund University, Sweden","institution_ids":["https://openalex.org/I187531555"]},{"raw_affiliation_string":"Lund Univ., Sweden#TAB#","institution_ids":["https://openalex.org/I187531555"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108819851","display_name":"Jens Johansson","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jens Johansson","raw_affiliation_strings":["System Verification, Malm\u00f6, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"System Verification, Malm\u00f6, Sweden","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078824435","display_name":"Mika M\u00e4ntyl\u00e4","orcid":"https://orcid.org/0000-0002-2841-5879"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Mika V. M\u00e4ntyl\u00e4","raw_affiliation_strings":["Aalto University, Helsinki, Finland","Aalto University,,,Helsinki,,Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University, Helsinki, Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Aalto University,,,Helsinki,,Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9986000061035156,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9986000061035156,"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/T10260","display_name":"Software Engineering Research","score":0.9976000189781189,"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/T11719","display_name":"Data Quality and Management","score":0.9955999851226807,"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/computer-science","display_name":"Computer science","score":0.7630257606506348},{"id":"https://openalex.org/keywords/rework","display_name":"Rework","score":0.6823804974555969},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6272439956665039},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5908504128456116},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5581336617469788},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.47626277804374695},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.44591429829597473},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4115182161331177},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2959707975387573},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08927938342094421}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7630257606506348},{"id":"https://openalex.org/C2776543023","wikidata":"https://www.wikidata.org/wiki/Q2147046","display_name":"Rework","level":2,"score":0.6823804974555969},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6272439956665039},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5908504128456116},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5581336617469788},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.47626277804374695},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.44591429829597473},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4115182161331177},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2959707975387573},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08927938342094421},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","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/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2652524.2652556","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2652524.2652556","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement","raw_type":"proceedings-article"},{"id":"pmh:oai:lup.lub.lu.se:ad808def-3b14-48e4-a0b7-cf22dca7f570","is_oa":true,"landing_page_url":"https://lup.lub.lu.se/record/4647034","pdf_url":null,"source":{"id":"https://openalex.org/S4306400536","display_name":"Lund University Publications (Lund University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I187531555","host_organization_name":"Lund University","host_organization_lineage":["https://openalex.org/I187531555"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferencePaper"}],"best_oa_location":{"id":"pmh:oai:lup.lub.lu.se:ad808def-3b14-48e4-a0b7-cf22dca7f570","is_oa":true,"landing_page_url":"https://lup.lub.lu.se/record/4647034","pdf_url":null,"source":{"id":"https://openalex.org/S4306400536","display_name":"Lund University Publications (Lund University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I187531555","host_organization_name":"Lund University","host_organization_lineage":["https://openalex.org/I187531555"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferencePaper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W61805229","https://openalex.org/W1532325895","https://openalex.org/W1983671301","https://openalex.org/W2006700268","https://openalex.org/W2079972013","https://openalex.org/W2125587588","https://openalex.org/W2130146200","https://openalex.org/W2139270835","https://openalex.org/W2156833313","https://openalex.org/W2158133897","https://openalex.org/W2165022036","https://openalex.org/W2167630669","https://openalex.org/W4245995216"],"related_works":["https://openalex.org/W2137196920","https://openalex.org/W2016750656","https://openalex.org/W2001967228","https://openalex.org/W1985548832","https://openalex.org/W1969836645","https://openalex.org/W2749019331","https://openalex.org/W1986499263","https://openalex.org/W2155301311","https://openalex.org/W36249452","https://openalex.org/W3151146928"],"abstract_inverted_index":{"Context:":[0],"Duplicate":[1],"detection":[2,47],"is":[3,65,132],"a":[4,15,23,76,80,140,158],"fundamental":[5],"part":[6],"of":[7,35,79,109,154],"issue":[8],"management.":[9],"Systems":[10],"able":[11],"to":[12],"predict":[13],"whether":[14],"new":[16],"defect":[17,95,129],"report":[18,130],"will":[19],"be":[20],"closed":[21],"as":[22,67,157],"duplicate,":[24],"may":[25],"decrease":[26],"costs":[27],"by":[28],"limiting":[29],"rework":[30],"and":[31,112],"collecting":[32],"related":[33],"pieces":[34],"information.":[36],"Goal:":[37],"Our":[38,149],"work":[39,150],"explores":[40],"using":[41,87,155],"Apache":[42],"Lucene":[43,88,122,156],"for":[44,89,161],"large-scale":[45],"duplicate":[46,162],"based":[48],"on":[49],"textual":[50],"content.":[51],"Also,":[52],"we":[53,103],"evaluate":[54],"the":[55,63,71,92,100,107,110,113,116,124,128,138,152],"previous":[56],"claim":[57],"that":[58,121],"results":[59,126],"are":[60],"improved":[61],"if":[62],"title":[64,111,131],"weighted":[66,133],"more":[68],"important":[69],"than":[70,137,143],"description.":[72],"Method:":[73],"We":[74,119],"conduct":[75],"conceptual":[77],"replication":[78],"well-cited":[81],"study":[82],"conducted":[83],"at":[84],"Sony":[85],"Ericsson,":[86],"searching":[90],"in":[91],"public":[93],"Android":[94],"repository.":[96],"In":[97],"line":[98],"with":[99],"original":[101],"study,":[102],"explore":[104],"how":[105],"varying":[106],"weighting":[108],"description":[114],"affects":[115],"accuracy.":[117],"Results:":[118],"show":[120],"obtains":[123],"best":[125],"when":[127],"three":[134],"times":[135],"higher":[136],"description,":[139],"bigger":[141],"difference":[142],"has":[144],"been":[145],"previously":[146],"acknowledged.":[147],"Conclusions:":[148],"shows":[151],"potential":[153],"scalable":[159],"solution":[160],"detection.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
