{"id":"https://openalex.org/W7125774320","doi":"https://doi.org/10.1145/3779153.3779181","title":"Leveraging BERT and LDA for Semi-Supervised Augmentation of Chinese Sexism Hate Speech Datasets","display_name":"Leveraging BERT and LDA for Semi-Supervised Augmentation of Chinese Sexism Hate Speech Datasets","publication_year":2025,"publication_date":"2025-11-07","ids":{"openalex":"https://openalex.org/W7125774320","doi":"https://doi.org/10.1145/3779153.3779181"},"language":null,"primary_location":{"id":"doi:10.1145/3779153.3779181","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3779153.3779181","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 9th International Conference on Big Data and Internet of Things","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3779153.3779181","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123973271","display_name":"Lexing Ruan","orcid":null},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lexing Ruan","raw_affiliation_strings":["Aberdeen Institute of Data Science and Artificial Intelligence, South China Normal University, Foshan, Guangdong, China"],"raw_orcid":"https://orcid.org/0009-0002-9311-413X","affiliations":[{"raw_affiliation_string":"Aberdeen Institute of Data Science and Artificial Intelligence, South China Normal University, Foshan, Guangdong, China","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123993416","display_name":"Jingyuan Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyuan Zhu","raw_affiliation_strings":["Aberdeen Institute of Data Science and Artificial Intelligence, South China Normal University, Foshan, Guangdong, China"],"raw_orcid":"https://orcid.org/0009-0003-3434-0695","affiliations":[{"raw_affiliation_string":"Aberdeen Institute of Data Science and Artificial Intelligence, South China Normal University, Foshan, Guangdong, China","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123994204","display_name":"Leying Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210120696","display_name":"South China Botanical Garden","ror":"https://ror.org/01xqdxh54","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210120696"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Leying Wang","raw_affiliation_strings":["Guangdong Country Garden School, Foshan, Guangdong, China"],"raw_orcid":"https://orcid.org/0009-0006-8021-363X","affiliations":[{"raw_affiliation_string":"Guangdong Country Garden School, Foshan, Guangdong, China","institution_ids":["https://openalex.org/I4210120696"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124013026","display_name":"Deng Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I106398593","display_name":"Mt. San Antonio College","ror":"https://ror.org/03wxx8465","country_code":"US","type":"education","lineage":["https://openalex.org/I106398593"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deng Lin","raw_affiliation_strings":["Mt. San Antonio College, Walnut, USA"],"raw_orcid":"https://orcid.org/0009-0001-7869-8889","affiliations":[{"raw_affiliation_string":"Mt. San Antonio College, Walnut, USA","institution_ids":["https://openalex.org/I106398593"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5123973271"],"corresponding_institution_ids":["https://openalex.org/I187400657"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.82858861,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"193","last_page":"201"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.940500020980835,"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":0.940500020980835,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.016599999740719795,"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":0.006099999882280827,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5644000172615051},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5227000117301941},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5131000280380249},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4778999984264374},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.43540000915527344},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.42649999260902405},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.42170000076293945},{"id":"https://openalex.org/keywords/latent-semantic-analysis","display_name":"Latent semantic analysis","score":0.35830000042915344},{"id":"https://openalex.org/keywords/computational-sociology","display_name":"Computational sociology","score":0.3125}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7278000116348267},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5874999761581421},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5792999863624573},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5644000172615051},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5227000117301941},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5131000280380249},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4778999984264374},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.43540000915527344},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.42649999260902405},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.42170000076293945},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.35830000042915344},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33469998836517334},{"id":"https://openalex.org/C126349790","wikidata":"https://www.wikidata.org/wiki/Q905036","display_name":"Computational sociology","level":2,"score":0.3125},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.28850001096725464},{"id":"https://openalex.org/C194051981","wikidata":"https://www.wikidata.org/wiki/Q1337691","display_name":"Economic shortage","level":3,"score":0.2856000065803528},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2752000093460083},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.2680000066757202},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.25850000977516174},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2563999891281128}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3779153.3779181","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3779153.3779181","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 9th International Conference on Big Data and Internet of Things","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3779153.3779181","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3779153.3779181","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 9th International Conference on Big Data and Internet of Things","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Gender equality","score":0.7781661152839661,"id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W357964226","https://openalex.org/W1981231959","https://openalex.org/W2109151141","https://openalex.org/W2144499799","https://openalex.org/W2166706824","https://openalex.org/W2612191247","https://openalex.org/W2896457183","https://openalex.org/W2952767732","https://openalex.org/W2952937483","https://openalex.org/W3035390927","https://openalex.org/W3105462247","https://openalex.org/W3154048149","https://openalex.org/W3191730131","https://openalex.org/W4385573759","https://openalex.org/W4389311369","https://openalex.org/W4409348161","https://openalex.org/W4410049584","https://openalex.org/W4410985811"],"related_works":[],"abstract_inverted_index":{"This":[0],"study":[1,105],"addresses":[2],"the":[3,42,90],"critical":[4],"shortage":[5],"of":[6],"culturally":[7],"nuanced":[8],"datasets":[9,36],"for":[10,46,117,129],"detecting":[11,118],"gender-based":[12],"hate":[13,81],"speech":[14,82],"in":[15,79,83,100,123],"Chinese":[16,35,84,124],"online":[17],"contexts":[18],"by":[19],"proposing":[20],"a":[21,107,113],"semi-supervised":[22],"learning":[23],"framework":[24,116],"that":[25,89],"combines":[26],"BERT":[27],"embeddings":[28],"and":[29,40,49,74,96,112,119,133],"LDA":[30,69],"topic":[31],"modeling.":[32],"Leveraging":[33],"existing":[34],"such":[37],"as":[38],"SWSR":[39],"BeyondGender,":[41],"method":[43],"employs":[44],"BERT-Chinese":[45],"text":[47],"vectorization":[48],"semantic":[50],"similarity":[51],"matching":[52],"to":[53,70],"efficiently":[54],"expand":[55],"annotated":[56],"data":[57],"with":[58,127],"minimal":[59],"manual":[60],"intervention.":[61],"The":[62,104],"expanded":[63],"dataset":[64,111],"is":[65],"then":[66],"analyzed":[67],"using":[68],"identify":[71],"latent":[72],"topics":[73],"examine":[75],"identity":[76],"construction":[77],"strategies":[78],"gendered":[80],"contexts.":[85],"Experimental":[86],"results":[87],"demonstrate":[88],"approach":[91],"effectively":[92],"improves":[93],"annotation":[94],"accuracy":[95],"model":[97],"performance,":[98],"particularly":[99],"identifying":[101],"hostile":[102],"language.":[103],"contributes":[106],"scalable,":[108],"high-quality":[109],"benchmark":[110],"robust":[114],"computational":[115],"analyzing":[120],"sexist":[121],"content":[122],"social":[125],"media,":[126],"implications":[128],"both":[130],"platform":[131],"governance":[132],"discourse":[134],"analysis.":[135]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-01-28T00:00:00"}