{"id":"https://openalex.org/W2890069879","doi":"https://doi.org/10.18653/v1/w18-5101","title":"Neural Character-based Composition Models for Abuse Detection","display_name":"Neural Character-based Composition Models for Abuse Detection","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2890069879","doi":"https://doi.org/10.18653/v1/w18-5101","mag":"2890069879"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w18-5101","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-5101","pdf_url":"https://www.aclweb.org/anthology/W18-5101.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":"Proceedings of the 2nd Workshop on Abusive Language Online (ALW2)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W18-5101.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002745343","display_name":"Pushkar Mishra","orcid":"https://orcid.org/0000-0002-1653-6198"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Pushkar Mishra","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083950817","display_name":"Helen Yannakoudakis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Helen Yannakoudakis","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5016184654","display_name":"Ekaterina Shutova","orcid":"https://orcid.org/0009-0003-6664-4474"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ekaterina Shutova","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5002745343"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8585,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.89172506,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9994000196456909,"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":0.9994000196456909,"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/T13629","display_name":"Text Readability and Simplification","score":0.9445000290870667,"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/computer-science","display_name":"Computer science","score":0.7147389054298401},{"id":"https://openalex.org/keywords/offensive","display_name":"Offensive","score":0.6633352637290955},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5786955952644348},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5232242941856384},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.5189146995544434},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5083686709403992},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4600420594215393},{"id":"https://openalex.org/keywords/obfuscation","display_name":"Obfuscation","score":0.4568077623844147},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4440239369869232},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.43129879236221313},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4259692132472992},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.3416788578033447},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.15195858478546143},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13233682513237}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7147389054298401},{"id":"https://openalex.org/C176856949","wikidata":"https://www.wikidata.org/wiki/Q2001676","display_name":"Offensive","level":2,"score":0.6633352637290955},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5786955952644348},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5232242941856384},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.5189146995544434},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5083686709403992},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4600420594215393},{"id":"https://openalex.org/C40305131","wikidata":"https://www.wikidata.org/wiki/Q2616305","display_name":"Obfuscation","level":2,"score":0.4568077623844147},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4440239369869232},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.43129879236221313},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4259692132472992},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3416788578033447},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.15195858478546143},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13233682513237},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.18653/v1/w18-5101","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-5101","pdf_url":"https://www.aclweb.org/anthology/W18-5101.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":"Proceedings of the 2nd Workshop on Abusive Language Online (ALW2)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1809.00378","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.00378","pdf_url":"https://arxiv.org/pdf/1809.00378","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:dare.uva.nl:publications/7c806103-c15a-4f4a-a788-a557e4b394a4","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/neural-characterbased-composition-models-for-abuse-detection(7c806103-c15a-4f4a-a788-a557e4b394a4).html","pdf_url":"https://pure.uva.nl/ws/files/49955210/W18_5101.pdf","source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Mishra, P, Yannakoudakis, H & Shutova, E 2018, Neural Character-based Composition Models for Abuse Detection. in D Fi\u0161er, R Huang, V Prabhakaran, R Voigt, Z Waseem & J Wernimont (eds), Second Workshop on Abusive Language Online : EMNLP 2018 : proceedings of the workshop, co-located with EMNLP 2018 : October 31, 2018, Brussels, Belgium. Stroudsburg, PA, pp. 1-10, 2nd Workshop on Abusive Language Online, 31/10/18. https://doi.org/10.18653/v1/W18-5101","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"mag:2890069879","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1809.00378","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:uvapub:oai:dare.uva.nl:publications/7c806103-c15a-4f4a-a788-a557e4b394a4","is_oa":true,"landing_page_url":"https://dare.uva.nl/personal/pure/en/publications/neural-characterbased-composition-models-for-abuse-detection(7c806103-c15a-4f4a-a788-a557e4b394a4).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Second Workshop on Abusive Language Online: EMNLP 2018 : proceedings of the workshop, co-located with EMNLP 2018 : October 31, 2018, Brussels, Belgium, 1 - 10","raw_type":"info:eu-repo/semantics/conferencepaper"},{"id":"doi:10.48550/arxiv.1809.00378","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1809.00378","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.18653/v1/w18-5101","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-5101","pdf_url":"https://www.aclweb.org/anthology/W18-5101.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":"Proceedings of the 2nd Workshop on Abusive Language Online (ALW2)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2890069879.pdf","grobid_xml":"https://content.openalex.org/works/W2890069879.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2963039068","https://openalex.org/W2540646130","https://openalex.org/W2768770989","https://openalex.org/W2948937448","https://openalex.org/W2969662548","https://openalex.org/W2976731213","https://openalex.org/W3142359849","https://openalex.org/W3201463115","https://openalex.org/W3020878096","https://openalex.org/W3129361063","https://openalex.org/W3157745232","https://openalex.org/W3102188065","https://openalex.org/W2922526444","https://openalex.org/W3193573834","https://openalex.org/W3034706370","https://openalex.org/W3144206916","https://openalex.org/W3134211956","https://openalex.org/W2964270319","https://openalex.org/W2789087924","https://openalex.org/W3046764764"],"abstract_inverted_index":{"The":[0,68],"advent":[1],"of":[2,18,31,44,51,65,71,97,155],"social":[3],"media":[4],"in":[5,104,158],"recent":[6],"years":[7],"has":[8],"fed":[9],"into":[10],"some":[11],"highly":[12],"undesirable":[13],"phenomena":[14],"such":[15,45],"as":[16],"proliferation":[17],"offensive":[19],"language,":[20],"hate":[21],"speech,":[22],"sexist":[23],"remarks,":[24],"etc.":[25],"on":[26,80,161],"the":[27,40,63,72,115,152,156],"Internet.":[28],"In":[29,126],"light":[30],"this,":[32],"there":[33],"have":[34],"been":[35],"several":[36],"efforts":[37],"to":[38,55,62,75,92,117],"automate":[39],"detection":[41,57,160],"and":[42,90,121,169],"moderation":[43],"abusive":[46,76],"content.":[47],"However,":[48,103],"deliberate":[49],"obfuscation":[50],"words":[52,112],"by":[53,133],"users":[54],"evade":[56],"poses":[58],"a":[59,93,106,135],"serious":[60],"challenge":[61],"effectiveness":[64],"these":[66],"efforts.":[67],"current":[69,153],"state":[70,154],"art":[73,157],"approaches":[74],"language":[77],"detection,":[78],"based":[79],"recurrent":[81],"neural":[82],"networks,":[83],"do":[84],"not":[85],"explicitly":[86],"address":[87,130],"this":[88,127,131],"problem":[89,132],"resort":[91],"generic":[94],"OOV":[95],"(out":[96],"vocabulary)":[98],"embedding":[99,108],"for":[100,109,141],"unseen":[101,111,142],"words.":[102,125,143],"using":[105],"single":[107],"all":[110],"we":[113,129],"lose":[114],"ability":[116],"distinguish":[118],"between":[119],"obfuscated":[120],"non-obfuscated":[122],"or":[123],"rare":[124],"paper,":[128],"designing":[134],"model":[136],"that":[137,147],"can":[138],"compose":[139],"embeddings":[140],"We":[144],"experimentally":[145],"demonstrate":[146],"our":[148],"approach":[149],"significantly":[150],"advances":[151],"abuse":[159],"datasets":[162],"from":[163],"two":[164],"different":[165],"domains,":[166],"namely":[167],"Twitter":[168],"Wikipedia":[170],"talk":[171],"page.":[172]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":5}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}