{"id":"https://openalex.org/W2089994405","doi":"https://doi.org/10.1145/1840784.1840829","title":"Evaluating text reuse discovery on the web","display_name":"Evaluating text reuse discovery on the web","publication_year":2010,"publication_date":"2010-08-18","ids":{"openalex":"https://openalex.org/W2089994405","doi":"https://doi.org/10.1145/1840784.1840829","mag":"2089994405"},"language":"en","primary_location":{"id":"doi:10.1145/1840784.1840829","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1840784.1840829","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the third symposium on Information interaction in context","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/conference_contribution/Evaluating_text_reuse_discovery_on_the_web/27376107","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075392907","display_name":"Stanford Chiu","orcid":null},"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":"Stanford Chiu","raw_affiliation_strings":["University of Massachusetts, Amherst, MA, USA","University of Massachusetts, Amherst, MA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University of Massachusetts, Amherst, MA, USA#TAB#","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019496352","display_name":"\u0130brahim UYSAL","orcid":"https://orcid.org/0000-0002-6767-0362"},"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":"Ibrahim Uysal","raw_affiliation_strings":["University of Massachusetts, Amherst, MA, USA","University of Massachusetts, Amherst, MA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University of Massachusetts, Amherst, MA, USA#TAB#","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, USA","University of Massachusetts, Amherst, MA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University of Massachusetts, Amherst, MA, USA#TAB#","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":0.2199,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.52537332,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"299","last_page":"304"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994999766349792,"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":0.9994999766349792,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9950000047683716,"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/reuse","display_name":"Reuse","score":0.9055691957473755},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8469505310058594},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6082773208618164},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.485965371131897},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.4763467609882355},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.45656949281692505},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3578605055809021},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07732030749320984},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06469589471817017}],"concepts":[{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.9055691957473755},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8469505310058594},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6082773208618164},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.485965371131897},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.4763467609882355},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.45656949281692505},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3578605055809021},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07732030749320984},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06469589471817017},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"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":5,"locations":[{"id":"doi:10.1145/1840784.1840829","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1840784.1840829","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the third symposium on Information interaction in context","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.366.7791","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.366.7791","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://maroo.cs.umass.edu/pub/web/getpdf.php?id=923","raw_type":"text"},{"id":"pmh:oai:researchbank.rmit.edu.au:rmit:19805","is_oa":false,"landing_page_url":"http://researchbank.rmit.edu.au/view/rmit:19805","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:alma61RMIT.INST:11246507520001341","is_oa":false,"landing_page_url":"http://doi.org/10.1145/1840784.1840829","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/27376107","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Evaluating_text_reuse_discovery_on_the_web/27376107","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":null,"raw_type":"Conference contribution"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/27376107","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Evaluating_text_reuse_discovery_on_the_web/27376107","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":null,"raw_type":"Conference contribution"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1494404649","https://openalex.org/W1596691921","https://openalex.org/W1967043694","https://openalex.org/W1983704604","https://openalex.org/W2012833704","https://openalex.org/W2044434631","https://openalex.org/W2119455368","https://openalex.org/W2129070169","https://openalex.org/W2148578434","https://openalex.org/W2148885851"],"related_works":["https://openalex.org/W2384475851","https://openalex.org/W2000444236","https://openalex.org/W2353602216","https://openalex.org/W2367078749","https://openalex.org/W2381798600","https://openalex.org/W1910583078","https://openalex.org/W2351618306","https://openalex.org/W2133117170","https://openalex.org/W2999162218","https://openalex.org/W1537443268"],"abstract_inverted_index":{"Text":[0],"reuse":[1,23,36,53],"detection":[2],"aims":[3],"to":[4,73],"identify":[5],"duplicates,":[6],"reformulations":[7],"or":[8],"partial":[9],"rewrites":[10],"of":[11,33],"a":[12,50,61],"given":[13],"text.":[14],"Some":[15],"previous":[16],"research":[17],"has":[18,40],"focused":[19],"on":[20,26,37,60],"determining":[21],"text":[22,35,52],"instances":[24],"accurately":[25],"local":[27],"corpora.":[28],"However,":[29],"the":[30,38,57,91],"practical":[31],"usage":[32],"finding":[34],"web":[39],"remained":[41],"largely":[42],"untested.":[43],"In":[44],"this":[45],"work,":[46],"we":[47],"1)":[48],"introduce":[49],"novel":[51],"searching":[54],"interface":[55],"for":[56],"web,":[58],"based":[59],"previously":[62],"proposed":[63],"architecture,":[64],"2)":[65],"evaluate":[66],"its":[67],"feasibility,":[68],"and":[69,77],"3)":[70],"investigate":[71],"techniques":[72],"improve":[74],"both":[75],"effectiveness":[76],"efficiency.":[78],"Our":[79],"results":[80],"show":[81],"that":[82],"exhaustive":[83],"query":[84],"submission":[85],"using":[86],"n-grams":[87],"can":[88],"dramatically":[89],"reduce":[90],"execution":[92],"time":[93],"with":[94],"only":[95],"small":[96],"losses":[97],"in":[98],"accuracy.":[99]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-08-27T14:10:00.468798","created_date":"2025-10-10T00:00:00"}
