{"id":"https://openalex.org/W4243754476","doi":"https://doi.org/10.1109/jcdl.2014.6970166","title":"Detecting and modeling local text reuse","display_name":"Detecting and modeling local text reuse","publication_year":2014,"publication_date":"2014-09-01","ids":{"openalex":"https://openalex.org/W4243754476","doi":"https://doi.org/10.1109/jcdl.2014.6970166"},"language":"en","primary_location":{"id":"doi:10.1109/jcdl.2014.6970166","doi":"https://doi.org/10.1109/jcdl.2014.6970166","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jcdl.2014.6970166","pdf_url":null,"source":{"id":"https://openalex.org/S4306417562","display_name":"ACM/IEEE Joint Conference on Digital Libraries","issn_l":"1552-5996","issn":["1552-5996"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Joint Conference on Digital Libraries","raw_type":"proceedings-article"},"volume":null,"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/A5101722493","display_name":"David A. Smith","orcid":"https://orcid.org/0000-0002-6636-6940","observed_orcids":["https://orcid.org/0000-0002-6636-6940"]},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David A. Smith","raw_affiliation_strings":["College of Computer and Information Science, Northeastern University Boston, MA, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer and Information Science, Northeastern University Boston, MA, U.S.A","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008390202","display_name":"Ryan Cordell","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryan Cordel","raw_affiliation_strings":["Northeastern University, Boston, MA, US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA, US","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008400357","display_name":"Elizabeth Maddock Dillon","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elizabeth Maddock Dillon","raw_affiliation_strings":["English Department, Northeastern University Boston, MA, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"English Department, Northeastern University Boston, MA, U.S.A","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021325471","display_name":"Nick Stramp","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nick Stramp","raw_affiliation_strings":["Political Science Department, University of Washington Seattle, WA, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Political Science Department, University of Washington Seattle, WA, U.S.A","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112036981","display_name":"John Wilkerson","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Wilkerson","raw_affiliation_strings":["Political Science Department, University of Washington Seattle, WA, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Political Science Department, University of Washington Seattle, WA, U.S.A","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":30.4337,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":{"value":0.99632561,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"183","last_page":"192"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12377","display_name":"Digital Humanities and Scholarship","score":0.47530001401901245,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12377","display_name":"Digital Humanities and Scholarship","score":0.47530001401901245,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.249099999666214,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"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/T10260","display_name":"Software Engineering Research","score":0.09059999883174896,"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/text-reuse-detection","display_name":"text reuse detection","score":0.8209999799728394},{"id":"https://openalex.org/keywords/document-clustering","display_name":"document clustering","score":0.5640000104904175},{"id":"https://openalex.org/keywords/social-networks","display_name":"social networks","score":0.5519999861717224},{"id":"https://openalex.org/keywords/nineteenth-century-america","display_name":"nineteenth-century United States","score":0.9259999990463257},{"id":"https://openalex.org/keywords/legislative-proposal","display_name":"draft legislation","score":0.5950000286102295},{"id":"https://openalex.org/keywords/united-states-congress","display_name":"United States Congress","score":0.906000018119812},{"id":"https://openalex.org/keywords/information-dissemination","display_name":"information dissemination","score":0.5860000252723694},{"id":"https://openalex.org/keywords/approximate-algorithms","display_name":"approximate algorithms","score":0.35199999809265137}],"concepts":[{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.8738851547241211},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7422380447387695},{"id":"https://openalex.org/C2777351106","wikidata":"https://www.wikidata.org/wiki/Q49371","display_name":"Legislation","level":2,"score":0.7301444411277771},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3742143511772156},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.354996919631958},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3396620452404022},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.1328044831752777},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.1286156177520752},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09741133451461792},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jcdl.2014.6970166","doi":"https://doi.org/10.1109/jcdl.2014.6970166","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jcdl.2014.6970166","pdf_url":null,"source":{"id":"https://openalex.org/S4306417562","display_name":"ACM/IEEE Joint Conference on Digital Libraries","issn_l":"1552-5996","issn":["1552-5996"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Joint Conference on Digital Libraries","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W32552433","https://openalex.org/W938539187","https://openalex.org/W1492995868","https://openalex.org/W1951628766","https://openalex.org/W1972174622","https://openalex.org/W2009904773","https://openalex.org/W2053107662","https://openalex.org/W2067272131","https://openalex.org/W2076489648","https://openalex.org/W2085922539","https://openalex.org/W2090320977","https://openalex.org/W2127492100","https://openalex.org/W2129070169","https://openalex.org/W2132399973","https://openalex.org/W2148578434","https://openalex.org/W2166036954","https://openalex.org/W2171150534","https://openalex.org/W4294541781"],"related_works":["https://openalex.org/W2250322150","https://openalex.org/W2099984129","https://openalex.org/W2148578434","https://openalex.org/W2089994405","https://openalex.org/W7097777106","https://openalex.org/W2594880443","https://openalex.org/W2247733540","https://openalex.org/W3186623843","https://openalex.org/W2221179916","https://openalex.org/W1523225232"],"abstract_inverted_index":{"Texts":[0],"propagate":[1],"through":[2],"many":[3],"social":[4],"networks":[5],"and":[6,14,50,79,97],"provide":[7],"evidence":[8],"for":[9,18],"their":[10],"structure.":[11],"We":[12,31],"describe":[13],"evaluate":[15,67],"efficient":[16],"algorithms":[17],"detecting":[19],"clusters":[20],"of":[21,42,53,71,82],"reused":[22],"passages":[23],"embedded":[24],"within":[25],"longer":[26],"documents":[27],"in":[28,45,57],"large":[29],"collections.":[30],"apply":[32],"these":[33,62],"techniques":[34,86],"to":[35,89],"two":[36],"case":[37,64],"studies:":[38],"analyzing":[39],"the":[40,46,51,58,69,72,80,83],"culture":[41],"free":[43],"reprinting":[44],"nineteenth-century":[47],"United":[48],"States":[49],"development":[52],"bills":[54],"into":[55],"legislation":[56],"U.S.":[59],"Congress.":[60],"Using":[61],"divergent":[63],"studies,":[65],"we":[66],"both":[68],"efficiency":[70],"approximate":[73],"local":[74],"text":[75],"reuse":[76],"detection":[77],"methods":[78],"accuracy":[81],"results.":[84],"These":[85],"allow":[87],"us":[88],"explore":[90],"how":[91],"ideas":[92,95],"spread,":[93,96],"which":[94,98],"subgroups":[99],"shared":[100],"ideas.":[101]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":5},{"year":2015,"cited_by_count":2}],"updated_date":"2026-10-26T11:51:55.731654","created_date":"2022-05-12T00:00:00"}