{"id":"https://openalex.org/W6968426158","doi":"https://doi.org/10.5281/zenodo.14654784","title":"NoisyHate","display_name":"NoisyHate","publication_year":2025,"publication_date":"2025-01-15","ids":{"openalex":"https://openalex.org/W6968426158","doi":"https://doi.org/10.5281/zenodo.14654784"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.14654784","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14654784","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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/10.5281/zenodo.14654784","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ye, Yiran","orcid":"https://orcid.org/0009-0009-0080-8679"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Yiran","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0009-0080-8679","affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Le, Thai","orcid":"https://orcid.org/0000-0001-9632-6870"},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Le, Thai","raw_affiliation_strings":["Indiana University"],"raw_orcid":"https://orcid.org/0000-0001-9632-6870","affiliations":[{"raw_affiliation_string":"Indiana University","institution_ids":["https://openalex.org/I592451"]}]},{"author_position":"last","author":{"id":null,"display_name":"Lee, Dongwon","orcid":"https://orcid.org/0000-0001-8371-7629"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lee, Dongwon","raw_affiliation_strings":["Pennsylvania State University University Park"],"raw_orcid":"https://orcid.org/0000-0001-8371-7629","affiliations":[{"raw_affiliation_string":"Pennsylvania State University University Park","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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/adversarial-system","display_name":"Adversarial system","score":0.6197999715805054},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5694000124931335},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.5442000031471252},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.4932999908924103},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.3634999990463257},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.2838999927043915}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6880000233650208},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6197999715805054},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5694000124931335},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.5442000031471252},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.4932999908924103},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4221000075340271},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36489999294281006},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3634999990463257},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3440999984741211},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3012000024318695},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.28870001435279846},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C162446236","wikidata":"https://www.wikidata.org/wiki/Q653137","display_name":"Content analysis","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.14654784","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14654784","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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:10.5281/zenodo.14654784","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14654784","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"NoisyHate:":[0],"Mining":[1],"and":[2,28,134,153,179,181,196],"Curating":[3],"Human-Written":[4],"Perturbations":[5],"for":[6],"Benchmarking":[7],"Content":[8],"Moderation":[9],"Models":[10],"Online":[11],"texts":[12],"with":[13],"toxic":[14,49,63,150,164],"content":[15,50],"are":[16,131],"a":[17,114],"clear":[18],"threat":[19],"to":[20,45,55,70,76,86,160],"the":[21,103],"users":[22],"on":[23,189],"social":[24],"media":[25],"in":[26,30,109,142,157],"particular":[27,158],"society":[29],"general.":[31],"Although":[32],"many":[33],"platforms":[34],"have":[35,52,82,144],"adopted":[36],"various":[37],"measures":[38,58],"(e.g.,":[39],"machine":[40],"learning-based":[41],"hate-speech":[42],"detection":[43,74,166],"systems)":[44],"diminish":[46],"their":[47],"effect,":[48],"writers":[51],"also":[53],"attempted":[54],"evade":[56],"such":[57,176,185,192],"by":[59,136],"using":[60],"cleverly":[61],"modified":[62],"words,":[64],"so-called":[65],"human-written":[66,119],"text":[67],"perturbations.":[68,107],"Therefore,":[69,108],"help":[71,161],"build":[72],"automatic":[73],"tools":[75],"recognize":[77],"those":[78],"perturbations,":[79,120],"prior":[80,148],"methods":[81],"developed":[83],"sophisticated":[84],"techniques":[85],"generate":[87],"diverse":[88],"adversarial":[89],"samples.":[90],"However,":[91],"we":[92,112],"note":[93],"that":[94,124,130,140],"these":[95],"``algorithms\"-generated":[96],"perturbations":[97,129,141],"do":[98],"not":[99],"necessarily":[100],"capture":[101],"all":[102],"traits":[104],"of":[105,118],"``human\"-written":[106],"this":[110],"paper,":[111],"introduce":[113],"novel,":[115],"high-quality":[116],"dataset":[117],"named":[121],"as":[122,177,186,193],"NoisyHate,":[123],"was":[125],"created":[126],"from":[127],"real-life":[128],"both":[132],"written":[133],"verified":[135],"human-in-the-loop.":[137],"We":[138,168],"show":[139],"NoisyHate":[143,171],"different":[145],"characteristics":[146],"than":[147],"algorithm-generated":[149],"datasets":[151],"show,":[152],"thus":[154],"can":[155],"be":[156],"useful":[159],"develop":[162],"better":[163],"speech":[165],"solutions.":[167],"thoroughly":[169],"validate":[170],"against":[172],"state-of-the-art":[173],"language":[174],"models,":[175],"BERT":[178],"RoBERTa,":[180],"black":[182],"box":[183],"APIs,":[184],"Perspective":[187],"API,":[188],"two":[190],"tasks,":[191],"perturbation":[194],"normalization":[195],"understanding.":[197]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}
