{"id":"https://openalex.org/W1983704604","doi":"https://doi.org/10.1145/1498759.1498835","title":"Finding text reuse on the web","display_name":"Finding text reuse on the web","publication_year":2009,"publication_date":"2009-02-09","ids":{"openalex":"https://openalex.org/W1983704604","doi":"https://doi.org/10.1145/1498759.1498835","mag":"1983704604"},"language":"en","primary_location":{"id":"doi:10.1145/1498759.1498835","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1498759.1498835","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032248436","display_name":"Michael Bendersky","orcid":"https://orcid.org/0000-0002-2941-6240"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Michael Bendersky","raw_affiliation_strings":["University of Massachusetts, Amherst, MA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, MA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105659698","display_name":"W. Bruce Croft","orcid":"https://orcid.org/0000-0003-2391-9629"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"W. Bruce Croft","raw_affiliation_strings":["University of Massachusetts, Amherst, MA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, MA","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5032248436"],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":23.2421,"has_fulltext":false,"cited_by_count":75,"citation_normalized_percentile":{"value":0.99298131,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"262","last_page":"271"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8159811496734619},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.8045524954795837},{"id":"https://openalex.org/keywords/timeline","display_name":"Timeline","score":0.7711065411567688},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6043289303779602},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5489178895950317},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.4795655608177185},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.42471417784690857},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4241105616092682},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4205082654953003},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08722361922264099}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8159811496734619},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.8045524954795837},{"id":"https://openalex.org/C4438859","wikidata":"https://www.wikidata.org/wiki/Q186117","display_name":"Timeline","level":2,"score":0.7711065411567688},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6043289303779602},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5489178895950317},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.4795655608177185},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.42471417784690857},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4241105616092682},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4205082654953003},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08722361922264099},{"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/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1145/1498759.1498835","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1498759.1498835","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:researchbank.rmit.edu.au:rmit:19857","is_oa":false,"landing_page_url":"http://researchbank.rmit.edu.au/view/rmit:19857","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":"Conference Paper"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.215.7083","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.215.7083","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.wsdm2009.org/papers/p262-bendersky.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.324.4408","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.324.4408","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ciir-publications.cs.umass.edu/pub/web/getpdf.php?id=857","raw_type":"text"},{"id":"pmh:oai:alma.61RMIT_INST:11246484570001341","is_oa":false,"landing_page_url":"http://doi.org/10.1145/1498759.1498835","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:figshare.com:article/27376494","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/27376494","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G491842410","display_name":null,"funder_award_id":"IIS-0534383","funder_id":"https://openalex.org/F4320337389","funder_display_name":"Division of Information and Intelligent Systems"}],"funders":[{"id":"https://openalex.org/F4320337389","display_name":"Division of Information and Intelligent Systems","ror":"https://ror.org/053a2cp42"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W91150412","https://openalex.org/W1577504169","https://openalex.org/W1596691921","https://openalex.org/W1980300190","https://openalex.org/W1993972354","https://openalex.org/W2012575882","https://openalex.org/W2012833704","https://openalex.org/W2018560257","https://openalex.org/W2037858832","https://openalex.org/W2040466507","https://openalex.org/W2044434631","https://openalex.org/W2055955951","https://openalex.org/W2066636486","https://openalex.org/W2069140227","https://openalex.org/W2070740689","https://openalex.org/W2085922539","https://openalex.org/W2093390569","https://openalex.org/W2094661073","https://openalex.org/W2103569001","https://openalex.org/W2107666336","https://openalex.org/W2111243605","https://openalex.org/W2128272588","https://openalex.org/W2129070169","https://openalex.org/W2138621811","https://openalex.org/W2148578434","https://openalex.org/W2148885851","https://openalex.org/W2152171734","https://openalex.org/W2169213601","https://openalex.org/W2170344111","https://openalex.org/W3158908792","https://openalex.org/W4206765718","https://openalex.org/W4246858749"],"related_works":["https://openalex.org/W2137912379","https://openalex.org/W2120222276","https://openalex.org/W143181582","https://openalex.org/W3025289787","https://openalex.org/W2404573736","https://openalex.org/W2167278502","https://openalex.org/W2036104219","https://openalex.org/W2389737178","https://openalex.org/W1986474863","https://openalex.org/W2937805521"],"abstract_inverted_index":{"With":[0],"the":[1,14,27,73,81,99,107,117,133,139,142,163],"overwhelming":[2],"number":[3],"of":[4,30,75,83,102,119,141],"reports":[5],"on":[6,13,106,138],"similar":[7],"events":[8],"originating":[9],"from":[10],"different":[11,53],"sources":[12,105],"web,":[15,108,143],"it":[16],"is":[17],"often":[18],"hard,":[19],"using":[20],"existing":[21],"web":[22,84,150],"search":[23,151],"paradigms,":[24],"to":[25,37,88],"find":[26],"original":[28,104],"source":[29],"&amp;quot;facts&amp;quot;,":[31],"statements,":[32],"rumors,":[33],"and":[34,36,64,125,156],"opinions,":[35],"track":[38],"their":[39],"development.":[40],"Several":[41],"techniques":[42,57,79,135],"have":[43,58],"been":[44,59],"previously":[45],"proposed":[46,134],"for":[47,122,152,161],"detecting":[48],"such":[49,109],"text":[50,76,89,154],"reuse":[51,77,90],"between":[52],"sources,":[54],"however":[55],"these":[56],"tested":[60],"against":[61],"relatively":[62],"small":[63],"homogeneous":[65],"TREC":[66],"collections.":[67],"In":[68,86],"this":[69],"work,":[70],"we":[71,92],"test":[72],"feasibility":[74],"detection":[78],"in":[80],"setting":[82],"search.":[85],"addition":[87],"detection,":[91],"develop":[93],"a":[94,112,158],"novel":[95],"technique":[96],"that":[97,132],"addresses":[98],"unique":[100],"challenges":[101],"finding":[103,153],"as":[110],"defining":[111],"timeline.":[113],"We":[114],"also":[115],"explore":[116],"use":[118],"link":[120],"analysis":[121],"identifying":[123],"reliable":[124],"relevant":[126],"reports.":[127],"Our":[128],"experimental":[129],"results":[130],"show":[131],"can":[136],"operate":[137],"scale":[140],"are":[144],"significantly":[145],"more":[146],"accurate":[147],"than":[148],"standard":[149],"reuse,":[155],"provide":[157],"richer":[159],"representation":[160],"tracking":[162],"information":[164],"flow.":[165]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":12}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
