{"id":"https://openalex.org/W2047449974","doi":"https://doi.org/10.1145/2396761.2398556","title":"Detecting offensive tweets via topical feature discovery over a large scale twitter corpus","display_name":"Detecting offensive tweets via topical feature discovery over a large scale twitter corpus","publication_year":2012,"publication_date":"2012-10-29","ids":{"openalex":"https://openalex.org/W2047449974","doi":"https://doi.org/10.1145/2396761.2398556","mag":"2047449974"},"language":"en","primary_location":{"id":"doi:10.1145/2396761.2398556","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2396761.2398556","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029285921","display_name":"Guang Xiang","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Guang Xiang","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA","Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027363073","display_name":"Bin Fan","orcid":"https://orcid.org/0000-0001-8149-6148"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bin Fan","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA","Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100398661","display_name":"Ling Wang","orcid":"https://orcid.org/0000-0001-8964-6454"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ling Wang","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA","Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090310268","display_name":"Jason Hong","orcid":"https://orcid.org/0000-0002-9856-9654"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Hong","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA","Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089539629","display_name":"Carolyn Penstein Ros\u00e9","orcid":"https://orcid.org/0000-0003-1128-5155"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carolyn Rose","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA","Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5029285921"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":11.4953,"has_fulltext":false,"cited_by_count":270,"citation_normalized_percentile":{"value":0.98444119,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1980","last_page":"1984"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9998999834060669,"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":0.9998999834060669,"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/T13959","display_name":"Swearing, Euphemism, Multilingualism","score":0.9883000254631042,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9606999754905701,"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/offensive","display_name":"Offensive","score":0.9258838891983032},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8062298893928528},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6714543700218201},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.661609947681427},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5754943490028381},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5719053149223328},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5579516291618347},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5418903827667236},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48562565445899963},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.46616679430007935},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43342939019203186},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4277753233909607},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3294793963432312},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09129714965820312},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07920214533805847}],"concepts":[{"id":"https://openalex.org/C176856949","wikidata":"https://www.wikidata.org/wiki/Q2001676","display_name":"Offensive","level":2,"score":0.9258838891983032},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8062298893928528},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6714543700218201},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.661609947681427},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5754943490028381},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5719053149223328},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5579516291618347},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5418903827667236},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48562565445899963},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.46616679430007935},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43342939019203186},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4277753233909607},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3294793963432312},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09129714965820312},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07920214533805847},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2396761.2398556","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2396761.2398556","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.303.1433","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.303.1433","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/%7Eguangx/papers/cikm12.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5699999928474426,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W112207403","https://openalex.org/W359818833","https://openalex.org/W1527758775","https://openalex.org/W1541379032","https://openalex.org/W1599835099","https://openalex.org/W1638659076","https://openalex.org/W1880262756","https://openalex.org/W1984251878","https://openalex.org/W2068017609","https://openalex.org/W2099653665","https://openalex.org/W2112251034","https://openalex.org/W2122369144","https://openalex.org/W2133108446","https://openalex.org/W2158551114","https://openalex.org/W2250904722","https://openalex.org/W2267835966","https://openalex.org/W2612120747","https://openalex.org/W3151392175","https://openalex.org/W4247225077","https://openalex.org/W6632417698"],"related_works":["https://openalex.org/W1568520348","https://openalex.org/W3214407891","https://openalex.org/W3194113117","https://openalex.org/W3213194066","https://openalex.org/W2967125893","https://openalex.org/W268355439","https://openalex.org/W4287020359","https://openalex.org/W4385323698","https://openalex.org/W2385362579","https://openalex.org/W2380993274"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,29,47,59,82],"novel":[6],"semi-supervised":[7],"approach":[8,17,43,57,104],"for":[9],"detecting":[10],"profanity-related":[11],"offensive":[12,35],"content":[13],"in":[14,21],"Twitter.":[15],"Our":[16,42,103],"exploits":[18],"linguistic":[19],"regularities":[20],"profane":[22],"language":[23],"via":[24],"statistical":[25],"topic":[26],"modeling":[27],"on":[28],"huge":[30],"Twitter":[31],"corpus,":[32],"and":[33],"detects":[34],"tweets":[36,69],"using":[37,70],"automatically":[38],"these":[39],"generated":[40],"features.":[41],"performs":[44],"competitively":[45],"with":[46],"variety":[48],"of":[49,64,84],"machine":[50],"learning":[51,118],"(ML)":[52],"algorithms.":[53],"For":[54],"instance,":[55],"our":[56],"achieves":[58],"true":[60],"positive":[61,90],"rate":[62,91],"(TP)":[63],"75.1%":[65],"over":[66],"4029":[67],"testing":[68],"Logistic":[71],"Regression,":[72],"significantly":[73],"outperforming":[74],"the":[75,88,94,98],"popular":[76],"keyword":[77],"matching":[78],"baseline,":[79],"which":[80],"has":[81],"TP":[83],"69.7%,":[85],"while":[86],"keeping":[87],"false":[89],"(FP)":[92],"at":[93,100],"same":[95],"level":[96],"as":[97],"baseline":[99],"about":[101],"3.77%.":[102],"provides":[105],"an":[106],"alternative":[107],"to":[108],"large":[109],"scale":[110],"hand":[111],"annotation":[112],"efforts":[113],"required":[114],"by":[115],"fully":[116],"supervised":[117],"approaches.":[119]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":24},{"year":2022,"cited_by_count":25},{"year":2021,"cited_by_count":37},{"year":2020,"cited_by_count":32},{"year":2019,"cited_by_count":29},{"year":2018,"cited_by_count":32},{"year":2017,"cited_by_count":27},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":14},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}