{"id":"https://openalex.org/W2991989988","doi":"https://doi.org/10.1109/kse.2019.8919436","title":"Design and Development of a Plagiarism Corpus in Thai for Plagiarism Detection","display_name":"Design and Development of a Plagiarism Corpus in Thai for Plagiarism Detection","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2991989988","doi":"https://doi.org/10.1109/kse.2019.8919436","mag":"2991989988"},"language":"en","primary_location":{"id":"doi:10.1109/kse.2019.8919436","is_oa":false,"landing_page_url":"https://doi.org/10.1109/kse.2019.8919436","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 11th International Conference on Knowledge and Systems Engineering (KSE)","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/A5008213060","display_name":"Santipong Thaiprayoon","orcid":"https://orcid.org/0000-0003-3021-474X"},"institutions":[{"id":"https://openalex.org/I1332092204","display_name":"National Science and Technology Development Agency","ror":"https://ror.org/04vy95b61","country_code":"TH","type":"government","lineage":["https://openalex.org/I1332092204"]},{"id":"https://openalex.org/I14316845","display_name":"National Electronics and Computer Technology Center","ror":"https://ror.org/04z82ry91","country_code":"TH","type":"government","lineage":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]}],"countries":["TH"],"is_corresponding":true,"raw_author_name":"Santipong Thaiprayoon","raw_affiliation_strings":["National Electronics and Computer Technology Center (NECTEC), National Science and Technology Development Agency (NSTDA), Pathumthani, Thailand"],"affiliations":[{"raw_affiliation_string":"National Electronics and Computer Technology Center (NECTEC), National Science and Technology Development Agency (NSTDA), Pathumthani, Thailand","institution_ids":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088300985","display_name":"Pornpimon Palingoon","orcid":null},"institutions":[{"id":"https://openalex.org/I14316845","display_name":"National Electronics and Computer Technology Center","ror":"https://ror.org/04z82ry91","country_code":"TH","type":"government","lineage":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]},{"id":"https://openalex.org/I1332092204","display_name":"National Science and Technology Development Agency","ror":"https://ror.org/04vy95b61","country_code":"TH","type":"government","lineage":["https://openalex.org/I1332092204"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Pornpimon Palingoon","raw_affiliation_strings":["National Electronics and Computer Technology Center (NECTEC), National Science and Technology Development Agency (NSTDA), Pathumthani, Thailand"],"affiliations":[{"raw_affiliation_string":"National Electronics and Computer Technology Center (NECTEC), National Science and Technology Development Agency (NSTDA), Pathumthani, Thailand","institution_ids":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009187258","display_name":"Kanokorn Trakultaweekoon","orcid":null},"institutions":[{"id":"https://openalex.org/I14316845","display_name":"National Electronics and Computer Technology Center","ror":"https://ror.org/04z82ry91","country_code":"TH","type":"government","lineage":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]},{"id":"https://openalex.org/I1332092204","display_name":"National Science and Technology Development Agency","ror":"https://ror.org/04vy95b61","country_code":"TH","type":"government","lineage":["https://openalex.org/I1332092204"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Kanokorn Trakultaweekoon","raw_affiliation_strings":["National Electronics and Computer Technology Center (NECTEC), National Science and Technology Development Agency (NSTDA), Pathumthani, Thailand"],"affiliations":[{"raw_affiliation_string":"National Electronics and Computer Technology Center (NECTEC), National Science and Technology Development Agency (NSTDA), Pathumthani, Thailand","institution_ids":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5008213060"],"corresponding_institution_ids":["https://openalex.org/I1332092204","https://openalex.org/I14316845"],"apc_list":null,"apc_paid":null,"fwci":0.14,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.58842879,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"18","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9945999979972839,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9945999979972839,"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":0.9934999942779541,"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/T11492","display_name":"Academic integrity and plagiarism","score":0.9916999936103821,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/plagiarism-detection","display_name":"Plagiarism detection","score":0.9185234308242798},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8218750953674316},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.6760307550430298},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6475633978843689},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6020090579986572},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5572333931922913},{"id":"https://openalex.org/keywords/obfuscation","display_name":"Obfuscation","score":0.5505627393722534},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48864394426345825},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.435322642326355}],"concepts":[{"id":"https://openalex.org/C2780907237","wikidata":"https://www.wikidata.org/wiki/Q2986238","display_name":"Plagiarism detection","level":2,"score":0.9185234308242798},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8218750953674316},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.6760307550430298},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6475633978843689},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6020090579986572},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5572333931922913},{"id":"https://openalex.org/C40305131","wikidata":"https://www.wikidata.org/wiki/Q2616305","display_name":"Obfuscation","level":2,"score":0.5505627393722534},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48864394426345825},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.435322642326355},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/kse.2019.8919436","is_oa":false,"landing_page_url":"https://doi.org/10.1109/kse.2019.8919436","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 11th International Conference on Knowledge and Systems Engineering (KSE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"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":17,"referenced_works":["https://openalex.org/W1544505227","https://openalex.org/W1967043694","https://openalex.org/W1967925097","https://openalex.org/W1974336599","https://openalex.org/W2099733782","https://openalex.org/W2147528976","https://openalex.org/W2340838113","https://openalex.org/W2401370751","https://openalex.org/W2888813522","https://openalex.org/W2905907858","https://openalex.org/W6632555176","https://openalex.org/W6643607630","https://openalex.org/W6703881407","https://openalex.org/W6712896141","https://openalex.org/W6754303591","https://openalex.org/W6757173239","https://openalex.org/W7039581999"],"related_works":["https://openalex.org/W4224216661","https://openalex.org/W3210347767","https://openalex.org/W98994209","https://openalex.org/W67940504","https://openalex.org/W2066014542","https://openalex.org/W2024170198","https://openalex.org/W2152144666","https://openalex.org/W2140282827","https://openalex.org/W2810872891","https://openalex.org/W2794792966"],"abstract_inverted_index":{"One":[0],"of":[1,5,43,104,111,175],"the":[2,22,30,35,63,131,135,147,158,170],"main":[3],"problems":[4],"creating":[6],"a":[7,17,39,44,81,87,166],"plagiarism":[8,46,52,65,83,89,113,176],"corpus":[9,47,58,100,136,159,181],"in":[10,134,161,169],"Thai":[11,45,69,82,88,112],"is":[12,15,59,182],"that":[13,130,157],"it":[14],"quite":[16],"difficult":[18],"task":[19],"to":[20,29,48,95],"acquire":[21],"plagiarized":[23,105],"documents":[24,106,133,149],"with":[25],"real":[26],"cases":[27,103],"due":[28],"copyright":[31],"issue.":[32],"To":[33],"solve":[34],"problem,":[36],"we":[37,79],"present":[38],"design":[40],"and":[41,50,72,86,114,125,152,173,184],"development":[42],"evaluate":[49],"compare":[51],"detection":[53,177],"algorithms":[54],"for":[55,91,187],"Thai.":[56],"The":[57],"developed":[60,160],"by":[61,140],"using":[62,141],"simulated":[64,102],"method":[66],"based":[67,107,123],"on":[68,108],"Wikipedia":[70],"articles":[71],"web":[73],"page":[74],"articles.":[75],"For":[76],"this":[77,162],"method,":[78],"provide":[80],"annotation":[84],"tool":[85],"guideline":[90],"assisting":[92],"human":[93],"annotators":[94],"plagiarize":[96],"text":[97],"passages.":[98],"Our":[99],"contains":[101],"four":[109],"classes":[110],"linguistic":[115],"mechanisms":[116],"including":[117],"copy-based":[118],"change,":[119,121,124],"lexicon-based":[120],"structure-":[122],"semantic-based":[126],"change.":[127],"We":[128,154],"show":[129],"suspicious":[132,148],"are":[137],"manually":[138],"created":[139],"different":[142],"obfuscation":[143],"strategies,":[144],"which":[145],"make":[146],"more":[150],"realistic":[151],"challenging.":[153],"then":[155],"believe":[156],"paper":[163],"will":[164],"be":[165],"valuable":[167],"contribution":[168],"development,":[171],"comparison,":[172],"evaluation":[174],"algorithms.":[178],"Moreover,":[179],"our":[180],"free":[183],"publicly":[185],"available":[186],"research":[188],"purposes.":[189]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
