{"id":"https://openalex.org/W2983149555","doi":"https://doi.org/10.1145/3357384.3358040","title":"Augment to Prevent","display_name":"Augment to Prevent","publication_year":2019,"publication_date":"2019-11-03","ids":{"openalex":"https://openalex.org/W2983149555","doi":"https://doi.org/10.1145/3357384.3358040","mag":"2983149555"},"language":"en","primary_location":{"id":"doi:10.1145/3357384.3358040","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3357384.3358040","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/71702/71702.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054300849","display_name":"Georgios Rizos","orcid":"https://orcid.org/0000-0003-2483-5574"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Georgios Rizos","raw_affiliation_strings":["Imperial College London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069476972","display_name":"Konstantin Hemker","orcid":"https://orcid.org/0009-0008-6414-0551"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Konstantin Hemker","raw_affiliation_strings":["Imperial College London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bj\u00f6rn Schuller","raw_affiliation_strings":["Imperial College London & University of Augsburg, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Imperial College London & University of Augsburg, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5054300849"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":7.5146,"has_fulltext":true,"cited_by_count":105,"citation_normalized_percentile":{"value":0.97742529,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"991","last_page":"1000"},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9745000004768372,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.9735000133514404,"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":0.798686146736145},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.679438591003418},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6279543042182922},{"id":"https://openalex.org/keywords/closeness","display_name":"Closeness","score":0.5961794853210449},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5329334139823914},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47964316606521606},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4734508693218231},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4711904525756836},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4667530357837677},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.45102447271347046},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4475105106830597},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.442003458738327},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4216267168521881},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4147902727127075},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.28775376081466675},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.28061193227767944},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.23522809147834778}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.798686146736145},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.679438591003418},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6279543042182922},{"id":"https://openalex.org/C2779545769","wikidata":"https://www.wikidata.org/wiki/Q5135364","display_name":"Closeness","level":2,"score":0.5961794853210449},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5329334139823914},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47964316606521606},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4734508693218231},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4711904525756836},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4667530357837677},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.45102447271347046},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4475105106830597},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.442003458738327},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4216267168521881},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4147902727127075},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.28775376081466675},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.28061193227767944},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.23522809147834778},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3357384.3358040","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3357384.3358040","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:71702","is_oa":true,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:bvb:384-opus4-717028","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/71702/71702.pdf","source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"bookpart"}],"best_oa_location":{"id":"pmh:oai:uni-augsburg.opus-bayern.de:71702","is_oa":true,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:bvb:384-opus4-717028","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/71702/71702.pdf","source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"bookpart"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.699999988079071}],"awards":[{"id":"https://openalex.org/G618429579","display_name":null,"funder_award_id":"HJ-25347","funder_id":"https://openalex.org/F4320322038","funder_display_name":"National Research Council for Economics, Humanities and Social Science"},{"id":"https://openalex.org/G6370123520","display_name":null,"funder_award_id":"ES/R00398X/1","funder_id":"https://openalex.org/F4320334630","funder_display_name":"Economic and Social Research Council"}],"funders":[{"id":"https://openalex.org/F4320320283","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10"},{"id":"https://openalex.org/F4320322038","display_name":"National Research Council for Economics, Humanities and Social Science","ror":"https://ror.org/012zp9903"},{"id":"https://openalex.org/F4320334630","display_name":"Economic and Social Research Council","ror":"https://ror.org/03n0ht308"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2983149555.pdf","grobid_xml":"https://content.openalex.org/works/W2983149555.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1071251684","https://openalex.org/W1600744878","https://openalex.org/W2081687495","https://openalex.org/W2163605009","https://openalex.org/W2181854537","https://openalex.org/W2250473257","https://openalex.org/W2250539671","https://openalex.org/W2398826216","https://openalex.org/W2398936787","https://openalex.org/W2399733683","https://openalex.org/W2467838519","https://openalex.org/W2473555522","https://openalex.org/W2509065397","https://openalex.org/W2513797604","https://openalex.org/W2559997609","https://openalex.org/W2563826943","https://openalex.org/W2564933006","https://openalex.org/W2610961739","https://openalex.org/W2613977835","https://openalex.org/W2740168486","https://openalex.org/W2806872289","https://openalex.org/W2963552443","https://openalex.org/W3098357269","https://openalex.org/W3103061166"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W2490526372","https://openalex.org/W4376166922","https://openalex.org/W4378510483","https://openalex.org/W4221142204"],"abstract_inverted_index":{"In":[0],"this":[1,28,77],"paper,":[2],"we":[3,79,97,119,128],"address":[4],"the":[5,33,42,58,85,91,107,115,168,172,195,198],"issue":[6],"of":[7,35,44,57,87,109,117,134,167],"augmenting":[8],"text":[9],"data":[10,101,150],"in":[11,27,142,189,197,209,214],"supervised":[12],"Natural":[13],"Language":[14],"Processing":[15],"problems,":[16],"exemplified":[17],"by":[18,47,204],"deep":[19,88,136],"online":[20,200],"hate":[21,36,92,139,191,201,215],"speech":[22,37,93,140,192,202,216],"classification.":[23],"A":[24],"great":[25],"challenge":[26],"domain":[29],"is":[30],"that":[31,60],"although":[32],"presence":[34],"can":[38,61,66,120],"be":[39,62],"deleterious":[40],"to":[41,68,72,90,113,144],"quality":[43],"service":[45],"provided":[46],"social":[48],"platforms,":[49],"it":[50],"still":[51],"comprises":[52],"only":[53],"a":[54,81,132,186],"tiny":[55],"fraction":[56],"content":[59],"found":[63],"online,":[64],"which":[65],"lead":[67],"performance":[69],"deterioration":[70],"due":[71],"majority":[73],"class":[74,110,217],"overfitting.":[75],"To":[76],"end,":[78],"perform":[80],"thorough":[82],"study":[83],"on":[84,131,155,160],"application":[86],"learning":[89],"detection":[94],"problem:":[95],"a)":[96,156],"propose":[98],"three":[99],"text-based":[100],"augmentation":[102,151],"techniques":[103,152],"aimed":[104],"at":[105],"reducing":[106],"degree":[108],"imbalance":[111],"and":[112,126,138,212],"maximise":[114],"amount":[116],"information":[118],"extract":[121],"from":[122],"our":[123],"limited":[124],"resources":[125],"b)":[127,165],"apply":[129],"them":[130],"selection":[133],"top-performing":[135],"architectures":[137],"databases":[141],"order":[143],"showcase":[145],"their":[146],"generalisation":[147],"properties.":[148],"The":[149],"are":[153],"based":[154,159],"synonym":[157],"replacement":[158],"word":[161,169],"embedding":[162],"vector":[163],"closeness,":[164],"warping":[166],"tokens":[170],"along":[171],"padded":[173],"sequence":[174],"or":[175],"c)":[176],"class-conditional,":[177],"recurrent":[178],"neural":[179],"language":[180],"generation.":[181],"Our":[182],"proposed":[183],"framework":[184],"yields":[185],"significant":[187],"increase":[188,208],"multi-class":[190],"detection,":[193],"outperforming":[194],"baseline":[196],"largest":[199],"database":[203],"an":[205],"absolute":[206],"5.7%":[207],"Macro-F1":[210],"score":[211],"30%":[213],"recall.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":16}],"updated_date":"2026-04-11T08:14:18.477133","created_date":"2019-11-22T00:00:00"}