{"id":"https://openalex.org/W4311604304","doi":"https://doi.org/10.1145/3575860","title":"Tamil Offensive Language Detection: Supervised versus Unsupervised Learning Approaches","display_name":"Tamil Offensive Language Detection: Supervised versus Unsupervised Learning Approaches","publication_year":2022,"publication_date":"2022-12-16","ids":{"openalex":"https://openalex.org/W4311604304","doi":"https://doi.org/10.1145/3575860"},"language":"en","primary_location":{"id":"doi:10.1145/3575860","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3575860","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-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/A5041573811","display_name":"Vimala Balakrishnan","orcid":"https://orcid.org/0000-0002-6859-4488"},"institutions":[{"id":"https://openalex.org/I33849332","display_name":"University of Malaya","ror":"https://ror.org/00rzspn62","country_code":"MY","type":"education","lineage":["https://openalex.org/I33849332"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Vimala Balakrishnan","raw_affiliation_strings":["Universiti Malaya, Malaysia"],"raw_orcid":"https://orcid.org/0000-0002-6859-4488","affiliations":[{"raw_affiliation_string":"Universiti Malaya, Malaysia","institution_ids":["https://openalex.org/I33849332"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080607996","display_name":"Vithyatheri Govindan","orcid":"https://orcid.org/0000-0003-1875-820X"},"institutions":[{"id":"https://openalex.org/I33849332","display_name":"University of Malaya","ror":"https://ror.org/00rzspn62","country_code":"MY","type":"education","lineage":["https://openalex.org/I33849332"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Vithyatheri Govindan","raw_affiliation_strings":["Universiti Malaya, Malaysia"],"raw_orcid":"https://orcid.org/0000-0003-1875-820X","affiliations":[{"raw_affiliation_string":"Universiti Malaya, Malaysia","institution_ids":["https://openalex.org/I33849332"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054654553","display_name":"Kumanan N. Govaichelvan","orcid":"https://orcid.org/0000-0002-3456-3472"},"institutions":[{"id":"https://openalex.org/I33849332","display_name":"University of Malaya","ror":"https://ror.org/00rzspn62","country_code":"MY","type":"education","lineage":["https://openalex.org/I33849332"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Kumanan N. Govaichelvan","raw_affiliation_strings":["Universiti Malaya, Malaysia"],"raw_orcid":"https://orcid.org/0000-0002-3456-3472","affiliations":[{"raw_affiliation_string":"Universiti Malaya, Malaysia","institution_ids":["https://openalex.org/I33849332"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I33849332"],"apc_list":null,"apc_paid":null,"fwci":1.5074,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.84865586,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"22","issue":"4","first_page":"1","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9998999834060669,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9998999834060669,"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/T13959","display_name":"Swearing, Euphemism, Multilingualism","score":0.9354000091552734,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"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/offensive","display_name":"Offensive","score":0.9219480752944946},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7822816371917725},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7360344529151917},{"id":"https://openalex.org/keywords/adaboost","display_name":"AdaBoost","score":0.6794377565383911},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6579645872116089},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6377143263816833},{"id":"https://openalex.org/keywords/tamil","display_name":"Tamil","score":0.6053017377853394},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5571514964103699},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5407192707061768},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.5170262455940247},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.4930121600627899},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4770966172218323},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4281194508075714},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.38285213708877563},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11742940545082092},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08651089668273926}],"concepts":[{"id":"https://openalex.org/C176856949","wikidata":"https://www.wikidata.org/wiki/Q2001676","display_name":"Offensive","level":2,"score":0.9219480752944946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7822816371917725},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7360344529151917},{"id":"https://openalex.org/C141404830","wikidata":"https://www.wikidata.org/wiki/Q2823869","display_name":"AdaBoost","level":3,"score":0.6794377565383911},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6579645872116089},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6377143263816833},{"id":"https://openalex.org/C140688305","wikidata":"https://www.wikidata.org/wiki/Q5885","display_name":"Tamil","level":2,"score":0.6053017377853394},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5571514964103699},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5407192707061768},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.5170262455940247},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.4930121600627899},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4770966172218323},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4281194508075714},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.38285213708877563},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11742940545082092},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08651089668273926},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3575860","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3575860","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8700000047683716,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1973003340","https://openalex.org/W2057108921","https://openalex.org/W2270941958","https://openalex.org/W2306599710","https://openalex.org/W2340954483","https://openalex.org/W2615499310","https://openalex.org/W2740168486","https://openalex.org/W2888083654","https://openalex.org/W2889171966","https://openalex.org/W2922580172","https://openalex.org/W2954226438","https://openalex.org/W2965052154","https://openalex.org/W2972084801","https://openalex.org/W2974335209","https://openalex.org/W3000478186","https://openalex.org/W3014487746","https://openalex.org/W3014629053","https://openalex.org/W3028751324","https://openalex.org/W3030198970","https://openalex.org/W3087096149","https://openalex.org/W3093080381","https://openalex.org/W3101583896","https://openalex.org/W3109126425","https://openalex.org/W3117237870","https://openalex.org/W3121117407","https://openalex.org/W3124917515","https://openalex.org/W3133538548","https://openalex.org/W3135420375","https://openalex.org/W3144309453","https://openalex.org/W3164279576","https://openalex.org/W3169224744","https://openalex.org/W3171716568","https://openalex.org/W3174740339","https://openalex.org/W3187767516","https://openalex.org/W3193548320","https://openalex.org/W3195139144","https://openalex.org/W3197959470","https://openalex.org/W3209214847","https://openalex.org/W4225705554","https://openalex.org/W4234453845","https://openalex.org/W4281569989","https://openalex.org/W4287064135","https://openalex.org/W4287322192","https://openalex.org/W4287905582","https://openalex.org/W4288413317","https://openalex.org/W4302472596","https://openalex.org/W4367726654","https://openalex.org/W4377374303","https://openalex.org/W4394659876","https://openalex.org/W6698085525"],"related_works":["https://openalex.org/W4386566602","https://openalex.org/W4200241924","https://openalex.org/W3023322875","https://openalex.org/W3041909748","https://openalex.org/W2922580172","https://openalex.org/W3184118381","https://openalex.org/W4287064724","https://openalex.org/W3117005508","https://openalex.org/W3032261270","https://openalex.org/W2955586496"],"abstract_inverted_index":{"Studies":[0],"on":[1,89],"natural":[2],"language":[3,30,65,161],"processing":[4],"are":[5,16],"mainly":[6],"conducted":[7],"in":[8,27,39,57,162],"English,":[9],"with":[10,131],"very":[11],"few":[12],"exploring":[13],"languages":[14],"that":[15,150],"under-resourced,":[17],"including":[18],"the":[19,61,103,108,151],"Dravidian":[20],"languages.":[21,164],"We":[22],"present":[23],"a":[24,32],"novel":[25],"work":[26],"detecting":[28],"offensive":[29,55,64,117,160],"using":[31,70],"corpus":[33],"collected":[34],"from":[35],"YouTube":[36],"containing":[37],"comments":[38],"Tamil.":[40],"The":[41],"study":[42],"specifically":[43],"aims":[44],"to":[45,101,115,124,158],"compare":[46],"two":[47],"machine":[48,72,112],"learning":[49,73,113],"approaches\u2014namely,":[50],"supervised":[51],"and":[52,84,86,140,145],"unsupervised\u2014to":[53],"detect":[54,116,159],"patterns":[56],"textual":[58],"communications.":[59,118],"In":[60],"first":[62],"setup,":[63],"detection":[66],"models":[67],"were":[68],"developed":[69],"traditional":[71],"algorithms":[74,114],"such":[75],"as":[76],"Random":[77],"Forest,":[78],"Logistic":[79],"Regression,":[80],"Support":[81],"Vector":[82],"Machine,":[83],"AdaBoost,":[85],"assessed":[87],"based":[88],"human":[90,129],"labeling.":[91],"Conversely,":[92],"we":[93],"used":[94,156],"K":[95,98],"-means":[96],"(":[97],"=":[99],"2)":[100],"cluster":[102],"unlabeled":[104],"data":[105],"before":[106],"training":[107],"same":[109],"set":[110],"of":[111,138],"Performance":[119],"scores":[120],"indicate":[121],"unsupervised":[122,152],"clustering":[123],"be":[125,155],"more":[126],"effective":[127],"than":[128],"labeling":[130],"ensemble":[132],"classifiers":[133],"achieving":[134],"an":[135],"impressive":[136],"accuracy":[137],"99.70%":[139],"99.87%":[141],"respectively":[142],"for":[143],"balanced":[144],"imbalanced":[146],"datasets,":[147],"hence":[148],"showing":[149],"approach":[153],"can":[154],"effectively":[157],"low-resourced":[163]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":1}],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2025-10-10T00:00:00"}