{"id":"https://openalex.org/W7126393806","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.133","title":"Unraveling the Dynamics of Semi-Supervised Hate Speech Detection: The Impact of Unlabeled Data Characteristics and Pseudo-Labeling Strategies","display_name":"Unraveling the Dynamics of Semi-Supervised Hate Speech Detection: The Impact of Unlabeled Data Characteristics and Pseudo-Labeling Strategies","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W7126393806","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.133"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2024.findings-eacl.133","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.133","pdf_url":"https://aclanthology.org/2024.findings-eacl.133.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.findings-eacl.133.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078640518","display_name":"F. Ludwig","orcid":null},"institutions":[{"id":"https://openalex.org/I1307569355","display_name":"Minnesota Department of Transportation","ror":"https://ror.org/04p63s850","country_code":"US","type":"government","lineage":["https://openalex.org/I1307569355"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Florian Ludwig","raw_affiliation_strings":["81677 Mnchen Zamdorfer Str. 88 81677 Mnchen Zamdorfer Str. 88 81677 Mnchen Universittsstrae 47 58097 Hagen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"81677 Mnchen Zamdorfer Str. 88 81677 Mnchen Zamdorfer Str. 88 81677 Mnchen Universittsstrae 47 58097 Hagen","institution_ids":["https://openalex.org/I1307569355"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031810809","display_name":"Klara Dolo\u0161","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Klara Dolos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124664930","display_name":"Ana Alves-Pinto","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ana Alves-Pinto","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5072459546","display_name":"Torsten Zesch","orcid":"https://orcid.org/0000-0002-9678-3825"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Torsten Zesch","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3055,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.70251562,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1974","last_page":"1986"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.951200008392334,"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":0.951200008392334,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.004800000227987766,"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/T12684","display_name":"Stuttering Research and Treatment","score":0.0035000001080334187,"subfield":{"id":"https://openalex.org/subfields/3203","display_name":"Clinical Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.5367000102996826},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.2549999952316284},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.24709999561309814},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.2401999980211258}],"concepts":[{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.5367000102996826},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4681999981403351},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3716999888420105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36230000853538513},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.29600000381469727},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.28040000796318054},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.27889999747276306},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2549999952316284},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.24709999561309814},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2401999980211258}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.findings-eacl.133","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.133","pdf_url":"https://aclanthology.org/2024.findings-eacl.133.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.findings-eacl.133","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.133","pdf_url":"https://aclanthology.org/2024.findings-eacl.133.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7126393806.pdf","grobid_xml":"https://content.openalex.org/works/W7126393806.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Despite":[0],"advances":[1],"in":[2,85,137,183],"machine":[3],"learning":[4,27],"based":[5],"hate":[6,89,148],"speech":[7,90],"detection,":[8],"the":[9,38,47,74,86,94,112,118,133,143,146,153,157,163,173,177,184],"need":[10],"for":[11,18,24,65,103],"larges":[12],"amounts":[13],"of":[14,40,76,82,88,96,100,114,135,152,156,162],"labeled":[15,50,167],"training":[16],"data":[17,34,42,53,97,115,170],"state-ofthe-art":[19],"approaches":[20],"remains":[21],"a":[22,78],"challenge":[23],"their":[25],"application.Semi-supervised":[26],"addresses":[28],"this":[29,44,70],"problem":[30,71],"by":[31,72,142],"leveraging":[32],"unlabeled":[33,52,169],"and":[35,51,99,150,168],"thus":[36],"reducing":[37],"amount":[39],"annotated":[41],"required.Underlying":[43],"approach":[45,165,179],"is":[46,140],"assumption":[48,57],"that":[49,111],"follow":[54],"similar":[55],"distributions.This":[56],"however":[58],"may":[59,180],"not":[60],"always":[61],"hold,":[62],"with":[63],"consequences":[64],"real":[66],"world":[67],"applications.We":[68],"address":[69],"investigating":[73],"dynamics":[75],"pseudo-labeling,":[77],"commonly":[79],"employed":[80],"form":[81],"semi-supervised":[83],"learning,":[84],"context":[87],"detection.Concretely":[91],"we":[92],"analysed":[93],"influence":[95,113],"characteristics":[98,116],"two":[101],"strategies":[102,129],"selecting":[104],"pseudo-labeled":[105],"samples:":[106],"threshold-and":[107],"ratio-based.The":[108],"results":[109,158],"show":[110],"on":[117,122],"pseudo-labeling":[119,136],"performances":[120],"depends":[121],"other":[123],"factors,":[124],"such":[125],"as":[126],"pseudo-label":[127],"selection":[128],"or":[130],"model":[131],"biases.Furthermore,":[132],"effectiveness":[134],"classification":[138],"performance":[139],"determined":[141],"interaction":[144],"between":[145],"number,":[147],"ratio":[149],"accuracy":[151],"selected":[154],"pseudo-labels.Analysis":[155],"suggests":[159],"an":[160],"advantage":[161],"thresholdbased":[164],"when":[166],"arise":[171],"from":[172],"same":[174],"domain,":[175],"whilst":[176],"ratio-based":[178],"be":[181],"recommended":[182],"opposite":[185],"situation.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-02T00:00:00"}