{"id":"https://openalex.org/W4393141410","doi":"https://doi.org/10.1109/ants59832.2023.10469000","title":"Detecting toxic comments from highly skewed social media data","display_name":"Detecting toxic comments from highly skewed social media data","publication_year":2023,"publication_date":"2023-12-17","ids":{"openalex":"https://openalex.org/W4393141410","doi":"https://doi.org/10.1109/ants59832.2023.10469000"},"language":"en","primary_location":{"id":"doi:10.1109/ants59832.2023.10469000","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ants59832.2023.10469000","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Advanced Networks and Telecommunications Systems (ANTS)","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/A5104264049","display_name":"Abhradeep Datta","orcid":null},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Abhradeep Datta","raw_affiliation_strings":["IIT Guwahati,Department of Mathematics,Assam,India"],"affiliations":[{"raw_affiliation_string":"IIT Guwahati,Department of Mathematics,Assam,India","institution_ids":["https://openalex.org/I1317621060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100995435","display_name":"B Monish Kumar","orcid":null},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"B Monish Kumar","raw_affiliation_strings":["IIT Guwahati,Data Science Programme,Assam,India"],"affiliations":[{"raw_affiliation_string":"IIT Guwahati,Data Science Programme,Assam,India","institution_ids":["https://openalex.org/I1317621060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035002083","display_name":"Ashok Singh Sairam","orcid":"https://orcid.org/0000-0001-9527-6496"},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ashok Singh Sairam","raw_affiliation_strings":["IIT Guwahati,Department of Mathematics,Assam,India"],"affiliations":[{"raw_affiliation_string":"IIT Guwahati,Department of Mathematics,Assam,India","institution_ids":["https://openalex.org/I1317621060"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5104264049"],"corresponding_institution_ids":["https://openalex.org/I1317621060"],"apc_list":null,"apc_paid":null,"fwci":0.1748,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.60611985,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"744","last_page":"749"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9958000183105469,"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":0.9958000183105469,"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/T10260","display_name":"Software Engineering Research","score":0.9538999795913696,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.920199990272522,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.6986321210861206},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5802609920501709},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.36271345615386963},{"id":"https://openalex.org/keywords/internet-privacy","display_name":"Internet privacy","score":0.35160213708877563},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.24723994731903076}],"concepts":[{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.6986321210861206},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5802609920501709},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.36271345615386963},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.35160213708877563},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.24723994731903076}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ants59832.2023.10469000","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ants59832.2023.10469000","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Advanced Networks and Telecommunications Systems (ANTS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1563088657","https://openalex.org/W2099813784","https://openalex.org/W2753546666","https://openalex.org/W2896457183","https://openalex.org/W2908694192","https://openalex.org/W2963748066","https://openalex.org/W2971296908","https://openalex.org/W2989817717","https://openalex.org/W3001219191","https://openalex.org/W3112028611","https://openalex.org/W3144206916","https://openalex.org/W3166550823","https://openalex.org/W3182965314","https://openalex.org/W4283736494","https://openalex.org/W6755207826"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":{"A":[0],"user\u2019s":[1,14],"online":[2],"social":[3,47],"media":[4,48],"data,":[5],"to":[6,76,90],"a":[7,23],"considerable":[8],"extent,":[9],"provides":[10],"insight":[11],"into":[12],"the":[13,60,78,143,165],"activity.":[15],"Screening":[16],"user-generated":[17],"data":[18,73,87,145],"for":[19],"negative":[20],"content":[21],"has":[22],"wide":[24],"range":[25],"of":[26,31,36,62,80,97],"applications,":[27],"like":[28],"background":[29],"checks":[30],"an":[32,92],"employee":[33],"and":[34,101,115,146],"spotting":[35],"terror":[37],"elements.":[38],"Researchers":[39],"have":[40],"focused":[41],"on":[42,142],"identifying":[43],"toxic":[44,64,159],"text":[45,65,139,160],"in":[46,53,164],"by":[49],"exploiting":[50],"deep-learning":[51],"models":[52],"conjunction":[54],"with":[55,137,157],"pre-trained":[56,131],"language":[57,132],"models.":[58],"However,":[59],"availability":[61],"labelled":[63,86],"is":[66,88],"limited.":[67],"In":[68],"this":[69],"work,":[70],"we":[71],"apply":[72],"augmentation":[74],"techniques":[75,141],"address":[77],"problem":[79],"imbalanced":[81],"training":[82,144],"data.":[83],"The":[84,94],"augmented":[85],"used":[89],"fine-tune":[91],"ensemble.":[93],"ensemble":[95],"consists":[96],"one":[98],"linear":[99],"classifier":[100],"three":[102],"sequence":[103],"classifiers,":[104],"Bi-RNN":[105],"(Bi-directional":[106,111,117,124],"Recurrent":[107,113],"Neural":[108],"Networks),":[109],"Bi-GRU":[110],"Gated":[112],"Unit),":[114],"Bi-LSTM":[116],"Long-Short":[118],"Term":[119],"Memory).":[120],"We":[121,134,152],"use":[122],"BERT":[123],"Encoder":[125],"Representations":[126],"from":[127],"Transformers)":[128],"as":[129],"our":[130,154],"model.":[133],"also":[135],"experiment":[136],"various":[138],"preprocessing":[140],"how":[147],"it":[148],"affects":[149],"classification":[150],"performance.":[151],"compare":[153],"best-identified":[155],"model":[156],"other":[158],"detection":[161],"frameworks":[162],"available":[163],"literature.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}