{"id":"https://openalex.org/W4285331802","doi":"https://doi.org/10.1109/ic2se52832.2021.9791999","title":"Document Similarity Detection using Rabin-Karp and Cosine Similarity Algorithms","display_name":"Document Similarity Detection using Rabin-Karp and Cosine Similarity Algorithms","publication_year":2021,"publication_date":"2021-11-16","ids":{"openalex":"https://openalex.org/W4285331802","doi":"https://doi.org/10.1109/ic2se52832.2021.9791999"},"language":"en","primary_location":{"id":"doi:10.1109/ic2se52832.2021.9791999","doi":"https://doi.org/10.1109/ic2se52832.2021.9791999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ic2se52832.2021.9791999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Conference on Computer Science and Engineering (IC2SE)","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/A5088970349","display_name":"Anggit Dwi Hartanto","orcid":"https://orcid.org/0000-0001-8091-8468","observed_orcids":["https://orcid.org/0000-0001-8091-8468"]},"institutions":[{"id":"https://openalex.org/I4400573182","display_name":"Universitas Amikom Yogyakarta","ror":"https://ror.org/00j65mz88","country_code":"ID","type":"education","lineage":["https://openalex.org/I4400573182"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Anggit Dwi Hartanto","raw_affiliation_strings":["Universitas AMIKOM,Department of Information System,Yogyakarta,Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitas AMIKOM,Department of Information System,Yogyakarta,Indonesia","institution_ids":["https://openalex.org/I4400573182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061132233","display_name":"Yoga Pristyanto","orcid":"https://orcid.org/0000-0002-1358-4864","observed_orcids":["https://orcid.org/0000-0002-1358-4864"]},"institutions":[{"id":"https://openalex.org/I4400573182","display_name":"Universitas Amikom Yogyakarta","ror":"https://ror.org/00j65mz88","country_code":"ID","type":"education","lineage":["https://openalex.org/I4400573182"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Yoga Pristyanto","raw_affiliation_strings":["Universitas AMIKOM,Department of Information System,Yogyakarta,Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitas AMIKOM,Department of Information System,Yogyakarta,Indonesia","institution_ids":["https://openalex.org/I4400573182"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034893427","display_name":"Andy Saputra","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4400573182","display_name":"Universitas Amikom Yogyakarta","ror":"https://ror.org/00j65mz88","country_code":"ID","type":"education","lineage":["https://openalex.org/I4400573182"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Andy Saputra","raw_affiliation_strings":["Universitas AMIKOM,Master Program of Informatics,Yogyakarta,Indonesia","Master Program of Informatics, Universitas AMIKOM, Yogyakarta, Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitas AMIKOM,Master Program of Informatics,Yogyakarta,Indonesia","institution_ids":["https://openalex.org/I4400573182"]},{"raw_affiliation_string":"Master Program of Informatics, Universitas AMIKOM, Yogyakarta, Indonesia","institution_ids":["https://openalex.org/I4400573182"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4400573182"],"apc_list":null,"apc_paid":null,"fwci":2.4906,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.91507006,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11492","display_name":"Academic integrity and plagiarism","score":0.6958000063896179,"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":0.6958000063896179,"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/T10260","display_name":"Software Engineering Research","score":0.11320000141859055,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.049300000071525574,"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":0.9860000014305115},{"id":"https://openalex.org/keywords/rabin-karp-algorithm","display_name":"Rabin-Karp algorithm","score":0.9779999852180481},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"cosine similarity","score":0.9929999709129333},{"id":"https://openalex.org/keywords/stemming","display_name":"stemming","score":0.8870000243186951},{"id":"https://openalex.org/keywords/university-theses","display_name":"academic theses","score":0.7620000243186951}],"concepts":[{"id":"https://openalex.org/C2780907237","wikidata":"https://www.wikidata.org/wiki/Q2986238","display_name":"Plagiarism detection","level":2,"score":0.8391519784927368},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.8038265705108643},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7928224205970764},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7451338768005371},{"id":"https://openalex.org/C2779207338","wikidata":"https://www.wikidata.org/wiki/Q9240","display_name":"Indonesian","level":2,"score":0.5655503869056702},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5348218083381653},{"id":"https://openalex.org/C178009071","wikidata":"https://www.wikidata.org/wiki/Q93344","display_name":"Trigonometric functions","level":2,"score":0.533371090888977},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.4704046845436096},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.4500957131385803},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.429127037525177},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39292633533477783},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.360160231590271},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2578081488609314},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17305266857147217},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ic2se52832.2021.9791999","doi":"https://doi.org/10.1109/ic2se52832.2021.9791999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ic2se52832.2021.9791999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Conference on Computer Science and Engineering (IC2SE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322730","display_name":"Kementerian Pendidikan","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2051560541","https://openalex.org/W2145009222","https://openalex.org/W2209915472","https://openalex.org/W2338630689","https://openalex.org/W2594232474","https://openalex.org/W2757705213","https://openalex.org/W2772134686","https://openalex.org/W2796433426","https://openalex.org/W2801524894","https://openalex.org/W2805550038","https://openalex.org/W2903619705","https://openalex.org/W2940504774","https://openalex.org/W2941563465","https://openalex.org/W2942765639","https://openalex.org/W2953786379","https://openalex.org/W2997227274","https://openalex.org/W2998426037","https://openalex.org/W3002412676","https://openalex.org/W3004566149","https://openalex.org/W3020436075","https://openalex.org/W3035537664","https://openalex.org/W3039321848","https://openalex.org/W3047996307","https://openalex.org/W3084541538","https://openalex.org/W3103959529","https://openalex.org/W4230485796"],"related_works":["https://openalex.org/W7219261834","https://openalex.org/W3210001360","https://openalex.org/W4412183928","https://openalex.org/W3005476947","https://openalex.org/W4241734023","https://openalex.org/W7216438537","https://openalex.org/W3041745064","https://openalex.org/W4393240412","https://openalex.org/W2739352024","https://openalex.org/W6995658382"],"abstract_inverted_index":{"Plagiarism":[0],"action":[1],"often":[2],"occurs":[3],"in":[4,13,16,42,70,130,151,172],"the":[5,17,21,63,97,103,107,118,134,145,154,161,181,186],"world":[6],"of":[7,11,24,62,99,127,147,158,196],"education.":[8],"One":[9,31],"example":[10],"plagiarism":[12],"education,":[14],"especially":[15,52,150,171],"university":[18],"environment,":[19],"is":[20,33,60,176,189],"frequent":[22],"occurrence":[23],"similarities":[25,41],"between":[26],"theses":[27],"made":[28],"by":[29,49],"students.":[30,55],"solution":[32,69],"to":[34,53,89,95,143,178],"develop":[35],"an":[36],"application":[37,94],"that":[38,45,65,133,185],"can":[39,46,66,140],"detect":[40,96,144],"thesis":[43],"documents":[44,101,126],"be":[47,67,141],"used":[48,142],"all":[50],"groups,":[51],"facilitate":[54],"Natural":[56],"Language":[57],"Processing":[58],"(NLP)":[59],"one":[61],"fields":[64],"a":[68,91,112,192],"developing":[71],"document":[72,169],"similarity":[73,98,146],"detection":[74],"applications.":[75],"In":[76,84],"this":[77,86,165],"study,":[78],"testing":[79],"focused":[80],"on":[81],"Indonesian":[82,100,131],"documents.":[83,173],"addition,":[85],"study":[87],"aims":[88],"build":[90],"system":[92],"or":[93],"using":[102,117,124],"Rabin-Karp":[104,135],"algorithm":[105,136,166,182],"with":[106,137,191],"Cosine":[108,138],"Similarity":[109,114,139],"method":[110],"as":[111],"Distance-Based":[113],"Measure":[115],"and":[116,160],"Stemming":[119],"technique.":[120],"The":[121],"experiment":[122],"results":[123],"15":[125],"scientific":[128],"publications":[129],"show":[132],"published":[148],"manuscripts,":[149],"Indonesian.":[152],"With":[153],"fastest":[155],"processing":[156,187],"time":[157,188],"seconds":[159],"longest":[162],"around.":[163],"seconds,":[164],"quickly":[167],"detects":[168],"similarities,":[170],"Further":[174],"research":[175],"recommended":[177],"optimize":[179],"from":[180],"side":[183],"so":[184],"faster":[190],"much":[193],"larger":[194],"number":[195],"words.":[197]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-10-27T15:51:10.671819","created_date":"2022-07-14T00:00:00"}
