{"id":"https://openalex.org/W2061263584","doi":"https://doi.org/10.1145/1324302.1324348","title":"A natural language processing approach to automatic plagiarism detection","display_name":"A natural language processing approach to automatic plagiarism detection","publication_year":2007,"publication_date":"2007-10-18","ids":{"openalex":"https://openalex.org/W2061263584","doi":"https://doi.org/10.1145/1324302.1324348","mag":"2061263584"},"language":"en","primary_location":{"id":"doi:10.1145/1324302.1324348","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1324302.1324348","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 SIGITE conference on Information technology education","raw_type":"proceedings-article"},"type":"article","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/A5110269178","display_name":"Chi-Hong Leung","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chi-Hong Leung","raw_affiliation_strings":["The Chinese University of Hong Kong, Shatin, N.T., Hong Kong","The Chinese University of Hong Kong, Shatin, N. T. Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shatin, N.T., Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Shatin, N. T. Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113436939","display_name":"Yuen-Yan Chan","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuen-Yan Chan","raw_affiliation_strings":["The Chinese University of Hong Kong, Shatin, N.T., Hong Kong","The Chinese University of Hong Kong, Shatin, N. T. Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shatin, N.T., Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Shatin, N. T. Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5110269178"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":1.8584,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.88345651,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"213","last_page":"218"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10028","display_name":"Topic Modeling","score":0.9908000230789185,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9732000231742859,"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/plagiarism-detection","display_name":"Plagiarism detection","score":0.9566627740859985},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8201550245285034},{"id":"https://openalex.org/keywords/synonym","display_name":"Synonym (taxonomy)","score":0.6787146925926208},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5594021677970886},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5538100004196167},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5398423671722412},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4843636453151703},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46339136362075806},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4128364324569702},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36608433723449707},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3572937548160553},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.19861489534378052},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15792042016983032}],"concepts":[{"id":"https://openalex.org/C2780907237","wikidata":"https://www.wikidata.org/wiki/Q2986238","display_name":"Plagiarism detection","level":2,"score":0.9566627740859985},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8201550245285034},{"id":"https://openalex.org/C173483453","wikidata":"https://www.wikidata.org/wiki/Q1040689","display_name":"Synonym (taxonomy)","level":3,"score":0.6787146925926208},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5594021677970886},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5538100004196167},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5398423671722412},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4843636453151703},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46339136362075806},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4128364324569702},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36608433723449707},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3572937548160553},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.19861489534378052},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15792042016983032},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C157369684","wikidata":"https://www.wikidata.org/wiki/Q34740","display_name":"Genus","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1324302.1324348","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1324302.1324348","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 SIGITE conference on Information technology education","raw_type":"proceedings-article"},{"id":"pmh:oai:hub.hku.hk:10722/134693","is_oa":false,"landing_page_url":"http://hdl.handle.net/10722/134693","pdf_url":null,"source":{"id":"https://openalex.org/S4377196271","display_name":"The HKU Scholars Hub (University of Hong Kong)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I889458895","host_organization_name":"University of Hong Kong","host_organization_lineage":["https://openalex.org/I889458895"],"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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8399999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1528319131","https://openalex.org/W2030825277","https://openalex.org/W2055869448","https://openalex.org/W2060862769","https://openalex.org/W2072818019","https://openalex.org/W2120851071","https://openalex.org/W2124479173","https://openalex.org/W2126491733","https://openalex.org/W2164548001","https://openalex.org/W2194023227","https://openalex.org/W2999879234","https://openalex.org/W4236682217","https://openalex.org/W4246648922","https://openalex.org/W4285719527","https://openalex.org/W6773357018"],"related_works":["https://openalex.org/W3168266056","https://openalex.org/W4287126803","https://openalex.org/W2112890327","https://openalex.org/W4250737080","https://openalex.org/W2735162248","https://openalex.org/W311440260","https://openalex.org/W2945111072","https://openalex.org/W2010433882","https://openalex.org/W1971922616","https://openalex.org/W3145472249"],"abstract_inverted_index":{"The":[0,35],"problem":[1,18],"of":[2,14,29,97],"plagiarism":[3,46,76,93,126],"has":[4],"existed":[5],"for":[6,43],"a":[7,109,148],"long":[8],"time":[9],"but":[10],"with":[11,58,111],"the":[12,17,69,75,81,98,121,136,152],"advance":[13],"information":[15],"technology":[16],"becomes":[19,159],"worse.":[20],"It":[21],"is":[22,37,66,88,104],"because":[23],"there":[24,146],"are":[25,135,145,155],"many":[26,142],"electronic":[27,73],"versions":[28],"published":[30],"materials":[31,154],"available":[32],"to":[33,54,56,91,106,161],"everyone.":[34],"Web":[36,70],"an":[38,64],"important":[39],"and":[40,119,139],"common":[41],"source":[42],"plagiarism.":[44,163],"Some":[45],"detection":[47,77,127],"programs":[48,128],"(such":[49],"as":[50],"Turnitin)":[51],"were":[52],"developed":[53],"attempt":[55],"deal":[57],"this":[59],"problem.":[60],"To":[61],"determine":[62],"whether":[63,132],"article":[65],"copied":[67,99,153],"from":[68],"or":[71],"other":[72],"sources,":[74],"program":[78],"should":[79],"calculate":[80],"similarity":[82],"between":[83],"two":[84,133],"articles.":[85],"However,":[86],"it":[87,103,158],"often":[89],"difficult":[90,160],"detect":[92,162],"accurately":[94],"after":[95],"modification":[96],"contents.":[100],"For":[101],"example,":[102],"possible":[105],"simply":[107],"replace":[108],"word":[110],"its":[112],"synonym":[113],"(e.g.":[114],"\"program\"":[115],"--":[116],"\"software":[117],"\")":[118],"change":[120],"entire":[122],"sentence":[123],"structure.":[124],"Most":[125],"can":[129],"only":[130],"compare":[131],"words":[134,144],"same":[137],"lexically":[138],"count":[140],"how":[141],"matched":[143],"in":[147],"paper.":[149],"Thus,":[150],"if":[151],"modified":[156],"deliberately,":[157]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":13},{"year":2013,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
