{"id":"https://openalex.org/W4283163477","doi":"https://doi.org/10.1017/s1351324922000262","title":"Automated hate speech detection and span extraction in underground hacking and extremist forums","display_name":"Automated hate speech detection and span extraction in underground hacking and extremist forums","publication_year":2022,"publication_date":"2022-06-20","ids":{"openalex":"https://openalex.org/W4283163477","doi":"https://doi.org/10.1017/s1351324922000262"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324922000262","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s1351324922000262","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/BAF99F7B84487806174DB29098B943A0/S1351324922000262a.pdf/div-class-title-automated-hate-speech-detection-and-span-extraction-in-underground-hacking-and-extremist-forums-div.pdf","source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/BAF99F7B84487806174DB29098B943A0/S1351324922000262a.pdf/div-class-title-automated-hate-speech-detection-and-span-extraction-in-underground-hacking-and-extremist-forums-div.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075372984","display_name":"Linda Zhou","orcid":"https://orcid.org/0000-0001-5503-9701"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Linda Zhou","raw_affiliation_strings":["Department of Computer Science and Technology, University of Cambridge, Cambridge CB2 1TN, UK"],"raw_orcid":"https://orcid.org/0000-0001-5503-9701","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, University of Cambridge, Cambridge CB2 1TN, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069029343","display_name":"Andrew Caines","orcid":"https://orcid.org/0000-0001-9647-4902"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrew Caines","raw_affiliation_strings":["Department of Computer Science and Technology, University of Cambridge, Cambridge CB2 1TN, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, University of Cambridge, Cambridge CB2 1TN, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030357891","display_name":"Ildik\u00f3 Pete","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ildiko Pete","raw_affiliation_strings":["Department of Computer Science and Technology, University of Cambridge, Cambridge CB2 1TN, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, University of Cambridge, Cambridge CB2 1TN, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055346534","display_name":"Alice Hutchings","orcid":"https://orcid.org/0000-0003-3037-2684"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alice Hutchings","raw_affiliation_strings":["Department of Computer Science and Technology, University of Cambridge, Cambridge CB2 1TN, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, University of Cambridge, Cambridge CB2 1TN, UK","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5075372984"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":1.9442,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.88029309,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"29","issue":"5","first_page":"1247","last_page":"1274"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":1.0,"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":1.0,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9765999913215637,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12519","display_name":"Cybercrime and Law Enforcement Studies","score":0.9610000252723694,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8012723922729492},{"id":"https://openalex.org/keywords/hacker","display_name":"Hacker","score":0.6591373682022095},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6478856801986694},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6368938088417053},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44981318712234497},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.4065232574939728},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3685472905635834},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32076606154441833},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.1702021360397339}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8012723922729492},{"id":"https://openalex.org/C86844869","wikidata":"https://www.wikidata.org/wiki/Q2798820","display_name":"Hacker","level":2,"score":0.6591373682022095},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6478856801986694},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6368938088417053},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44981318712234497},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.4065232574939728},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3685472905635834},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32076606154441833},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.1702021360397339}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1017/s1351324922000262","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s1351324922000262","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/BAF99F7B84487806174DB29098B943A0/S1351324922000262a.pdf/div-class-title-automated-hate-speech-detection-and-span-extraction-in-underground-hacking-and-extremist-forums-div.pdf","source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},{"id":"pmh:oai:www.repository.cam.ac.uk:1810/341196","is_oa":true,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/341196","pdf_url":null,"source":{"id":"https://openalex.org/S4306401777","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"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":null,"raw_type":"Article"},{"id":"doi:10.17863/cam.88621","is_oa":true,"landing_page_url":"https://doi.org/10.17863/cam.88621","pdf_url":null,"source":{"id":"https://openalex.org/S7407050737","display_name":"Apollo","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":"article-journal"}],"best_oa_location":{"id":"doi:10.1017/s1351324922000262","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s1351324922000262","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/BAF99F7B84487806174DB29098B943A0/S1351324922000262a.pdf/div-class-title-automated-hate-speech-detection-and-span-extraction-in-underground-hacking-and-extremist-forums-div.pdf","source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4283163477.pdf","grobid_xml":"https://content.openalex.org/works/W4283163477.grobid-xml"},"referenced_works_count":67,"referenced_works":["https://openalex.org/W80056832","https://openalex.org/W1566289585","https://openalex.org/W1614298861","https://openalex.org/W1975879668","https://openalex.org/W2084907416","https://openalex.org/W2087347434","https://openalex.org/W2101234009","https://openalex.org/W2120354757","https://openalex.org/W2131631242","https://openalex.org/W2144211451","https://openalex.org/W2147880316","https://openalex.org/W2157354643","https://openalex.org/W2164777277","https://openalex.org/W2250539671","https://openalex.org/W2271840356","https://openalex.org/W2473555522","https://openalex.org/W2493916176","https://openalex.org/W2540646130","https://openalex.org/W2595653137","https://openalex.org/W2613977835","https://openalex.org/W2798110387","https://openalex.org/W2806872289","https://openalex.org/W2891177506","https://openalex.org/W2891270452","https://openalex.org/W2896457183","https://openalex.org/W2897256503","https://openalex.org/W2903241493","https://openalex.org/W2947343938","https://openalex.org/W2953646920","https://openalex.org/W2954189785","https://openalex.org/W2954226438","https://openalex.org/W2954566102","https://openalex.org/W2956090150","https://openalex.org/W2959053582","https://openalex.org/W2963042536","https://openalex.org/W2963748441","https://openalex.org/W2963943967","https://openalex.org/W2972735048","https://openalex.org/W2973806433","https://openalex.org/W2979826702","https://openalex.org/W2989817717","https://openalex.org/W2990622393","https://openalex.org/W2993259699","https://openalex.org/W2998704965","https://openalex.org/W3000571327","https://openalex.org/W3011411500","https://openalex.org/W3011893736","https://openalex.org/W3013437827","https://openalex.org/W3015536985","https://openalex.org/W3028244287","https://openalex.org/W3030494570","https://openalex.org/W3106580412","https://openalex.org/W3113763975","https://openalex.org/W3115373420","https://openalex.org/W3115453555","https://openalex.org/W3116231956","https://openalex.org/W3130857423","https://openalex.org/W3137546015","https://openalex.org/W4241900191","https://openalex.org/W6603174692","https://openalex.org/W6631190155","https://openalex.org/W6675354045","https://openalex.org/W6680532216","https://openalex.org/W6739901393","https://openalex.org/W6762286336","https://openalex.org/W6778004076","https://openalex.org/W6828643406"],"related_works":["https://openalex.org/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2081671587","https://openalex.org/W1151175420","https://openalex.org/W2131711534","https://openalex.org/W2559837139","https://openalex.org/W2541680182","https://openalex.org/W2559040841"],"abstract_inverted_index":{"Abstract":[0],"Hate":[1],"speech":[2,43,62,124,151,190],"is":[3,44,183],"any":[4],"kind":[5],"of":[6,29,41,80,102,116,127,168,224],"communication":[7],"that":[8,47,161],"attacks":[9],"a":[10,13,122,148,155,162,178],"person":[11],"or":[12],"group":[14],"based":[15],"on":[16,57,165,187],"their":[17,36],"characteristics,":[18],"such":[19],"as":[20],"gender,":[21],"religion":[22],"and":[23,59,66,71,78,136,138,204,211,220],"race.":[24],"Due":[25],"to":[26,50,89,97,109,153,177],"the":[27,39,90,99,114,174,184],"availability":[28],"online":[30,133],"platforms":[31],"where":[32,69],"people":[33],"can":[34],"express":[35],"(hateful)":[37],"opinions,":[38],"amount":[40],"hate":[42,52,61,117,123,150,189],"steadily":[45],"increasing":[46],"often":[48],"leads":[49],"offline":[51],"crimes.":[53],"This":[54,119],"paper":[55,120,196],"focuses":[56],"understanding":[58],"detecting":[60],"in":[63,107],"underground":[64],"hacking":[65,134],"extremist":[67,141],"forums":[68],"cybercriminals":[70],"extremists,":[72],"respectively,":[73],"communicate":[74],"with":[75,84,113,147],"each":[76],"other,":[77],"some":[79],"them":[81],"are":[82],"associated":[83],"criminal":[85],"activity.":[86],"Moreover,":[87],"due":[88],"lengthy":[91],"posts,":[92],"it":[93],"would":[94],"be":[95],"beneficial":[96],"identify":[98],"specific":[100],"span":[101,209],"text":[103],"containing":[104],"hateful":[105,218],"content":[106],"order":[108],"assist":[110],"site":[111],"moderators":[112],"removal":[115],"speech.":[118],"describes":[121],"dataset":[125,146,152],"composed":[126],"posts":[128],"extracted":[129],"from":[130,192,202],"HackForums,":[131],"an":[132,222],"forum,":[135],"Stormfront":[137],"Incels.co,":[139],"two":[140,206],"forums.":[142],"We":[143],"combined":[144],"our":[145],"Twitter":[149],"train":[154],"multi-platform":[156],"classifier.":[157,180],"Our":[158],"evaluation":[159],"shows":[160],"classifier":[163],"trained":[164],"multiple":[166],"sources":[167],"data":[169],"does":[170],"not":[171],"always":[172],"improve":[173],"performance":[175],"compared":[176],"mono-platform":[179],"Finally,":[181],"this":[182],"first":[185],"work":[186],"extracting":[188],"spans":[191,219],"longer":[193],"texts.":[194],"The":[195],"fine-tunes":[197],"BERT":[198],"(Bidirectional":[199],"Encoder":[200],"Representations":[201],"Transformers)":[203],"adopts":[205],"approaches":[207,215],"\u2013":[208],"prediction":[210],"sequence":[212],"labelling.":[213],"Both":[214],"successfully":[216],"extract":[217],"achieve":[221],"F1-score":[223],"at":[225],"least":[226],"69%.":[227]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":4}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}