{"id":"https://openalex.org/W6963886818","doi":"https://doi.org/10.21227/0bsx-z948","title":"BengaliSent140 - A Bengali Hate Speech Fusion Dataset","display_name":"BengaliSent140 - A Bengali Hate Speech Fusion Dataset","publication_year":2024,"publication_date":"2024-03-17","ids":{"openalex":"https://openalex.org/W6963886818","doi":"https://doi.org/10.21227/0bsx-z948"},"language":"en","primary_location":{"id":"doi:10.21227/0bsx-z948","is_oa":true,"landing_page_url":"https://doi.org/10.21227/0bsx-z948","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.21227/0bsx-z948","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Islam, Akif","orcid":null},"institutions":[{"id":"https://openalex.org/I902853133","display_name":"University of Rajshahi","ror":"https://ror.org/05nnyr510","country_code":"BD","type":"education","lineage":["https://openalex.org/I902853133"]}],"countries":["BD"],"is_corresponding":true,"raw_author_name":"Islam, Akif","raw_affiliation_strings":["Department of CSE, University of Rajshahi"],"affiliations":[{"raw_affiliation_string":"Department of CSE, University of Rajshahi","institution_ids":["https://openalex.org/I902853133"]}]},{"author_position":"last","author":{"id":null,"display_name":"Kumar Roy, Sujan","orcid":null},"institutions":[{"id":"https://openalex.org/I902853133","display_name":"University of Rajshahi","ror":"https://ror.org/05nnyr510","country_code":"BD","type":"education","lineage":["https://openalex.org/I902853133"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Kumar Roy, Sujan","raw_affiliation_strings":["Department of CSE, University of Rajshahi"],"affiliations":[{"raw_affiliation_string":"Department of CSE, University of Rajshahi","institution_ids":["https://openalex.org/I902853133"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I902853133"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/bengali","display_name":"Bengali","score":0.9416999816894531},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5357000231742859},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.39590001106262207},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.34700000286102295},{"id":"https://openalex.org/keywords/offensive","display_name":"Offensive","score":0.3224000036716461}],"concepts":[{"id":"https://openalex.org/C19235068","wikidata":"https://www.wikidata.org/wiki/Q9610","display_name":"Bengali","level":2,"score":0.9416999816894531},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5784000158309937},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5357000231742859},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40369999408721924},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.39590001106262207},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38749998807907104},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C176856949","wikidata":"https://www.wikidata.org/wiki/Q2001676","display_name":"Offensive","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.26989999413490295},{"id":"https://openalex.org/C123406163","wikidata":"https://www.wikidata.org/wiki/Q82042","display_name":"Part of speech","level":2,"score":0.25850000977516174}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21227/0bsx-z948","is_oa":true,"landing_page_url":"https://doi.org/10.21227/0bsx-z948","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"dataset"}],"best_oa_location":{"id":"doi:10.21227/0bsx-z948","is_oa":true,"landing_page_url":"https://doi.org/10.21227/0bsx-z948","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dataset"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7242392301559448,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"today's":[1],"world":[2],"of":[3,40,141],"online":[4],"communication,":[5],"hate":[6,16,27,50,81,113,146,165,184],"speech":[7,17,51,82,114,147,185],"is":[8,54,85,107,139],"a":[9,195],"big":[10,105],"problem.":[11],"This":[12,137],"dataset":[13,138,151],"focuses":[14],"on":[15,43,59],"in":[18,52,83,101,191],"Bengali,":[19],"analyzing":[20],"speeches":[21],"to":[22,35,77,160,180],"see":[23],"if":[24,162],"they":[25,163],"contain":[26,164],"or":[28,166],"not.":[29,167],"While":[30],"there":[31,88,109],"are":[32,72,134],"many":[33,111],"ways":[34,179],"analyze":[36],"text":[37],"online,":[38],"most":[39],"them":[41],"focus":[42],"languages":[44],"like":[45,61,171],"English,":[46],"leaving":[47],"out":[48],"Bengali. But":[49],"Bengali":[53,84,112,145],"serious":[55],"and":[56,63,79,131,156,175,182,197],"common,":[57],"especially":[58],"platforms":[60],"Facebook":[62],"YouTube.":[64],"Sometimes,":[65],"even":[66],"TV":[67],"shows":[68],"have":[69],"comments":[70],"that":[71,108,133],"not":[73,135],"nice":[74],"for":[75,92,144,200],"everyone":[76],"see. Finding":[78],"stopping":[80],"hard":[86],"because":[87],"aren't":[89],"good":[90],"tools":[91],"it":[93],"yet.":[94],"That's":[95],"why":[96],"we":[97,120],"need":[98],"more":[99,169],"research":[100],"this":[102,150,172],"area.":[103],"One":[104],"problem":[106],"weren't":[110],"datasets":[115,155],"available":[116],"before":[117],"ours.":[118],"So,":[119],"made":[121,149],"one":[122,140],"with":[123],"around":[124],"140,000":[125],"speeches,":[126],"including":[127],"68,000":[128],"hateful":[129],"ones":[130],"71,000":[132],"hateful.":[136],"the":[142,193],"biggest":[143],"online. We":[148],"by":[152],"combining":[153],"different":[154],"changing":[157],"their":[158],"labels":[159],"show":[161],"Having":[168],"data":[170],"helps":[173],"researchers":[174],"computers":[176],"learn":[177],"better":[178],"find":[181],"stop":[183],"online.":[186],"It's":[187],"an":[188],"important":[189],"step":[190],"making":[192],"internet":[194],"safer":[196],"kinder":[198],"place":[199],"everyone. ":[201]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}