{"id":"https://openalex.org/W2913044599","doi":null,"title":"Merging Datasets for Aggressive Text Identification","display_name":"Merging Datasets for Aggressive Text Identification","publication_year":2018,"publication_date":"2018-08-01","ids":{"openalex":"https://openalex.org/W2913044599","mag":"2913044599"},"language":"en","primary_location":{"id":"mag:2913044599","doi":null,"is_oa":false,"landing_page_url":"https://www.aclweb.org/anthology/W18-4416.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419219","display_name":"International Conference on Computational Linguistics","issn_l":"1525-2477","issn":["1525-2477"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Computational Linguistics","raw_type":null},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"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/A5024011151","display_name":"Paula Fortuna","orcid":"https://orcid.org/0000-0002-2306-9276","observed_orcids":["https://orcid.org/0000-0002-2306-9276"]},"institutions":[{"id":"https://openalex.org/I182534213","display_name":"Universidade do Porto","ror":"https://ror.org/043pwc612","country_code":"PT","type":"education","lineage":["https://openalex.org/I182534213"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Paula Fortuna","raw_affiliation_strings":["Universidade do Porto, Porto, Portugal"],"raw_orcid":"https://orcid.org/0000-0002-2306-9276","affiliations":[{"raw_affiliation_string":"Universidade do Porto, Porto, Portugal","institution_ids":["https://openalex.org/I182534213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067041465","display_name":"Jos\u00e9 Vasconcelos Ferreira","orcid":"https://orcid.org/0000-0002-5577-8237","observed_orcids":["https://orcid.org/0000-0002-5577-8237"]},"institutions":[{"id":"https://openalex.org/I182534213","display_name":"Universidade do Porto","ror":"https://ror.org/043pwc612","country_code":"PT","type":"education","lineage":["https://openalex.org/I182534213"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 Vasconcelos Ferreira","raw_affiliation_strings":["Universidade do Porto, Porto, Portugal"],"raw_orcid":"https://orcid.org/0000-0002-5577-8237","affiliations":[{"raw_affiliation_string":"Universidade do Porto, Porto, Portugal","institution_ids":["https://openalex.org/I182534213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046109768","display_name":"Luiz Pires","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luiz Pires","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065653560","display_name":"Guilherme Routar","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guilherme Routar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5065124975","display_name":"S\u00e9rgio Nunes","orcid":"https://orcid.org/0000-0002-2693-988X","observed_orcids":["https://orcid.org/0000-0002-2693-988X"]},"institutions":[{"id":"https://openalex.org/I182534213","display_name":"Universidade do Porto","ror":"https://ror.org/043pwc612","country_code":"PT","type":"education","lineage":["https://openalex.org/I182534213"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"S\u00e9rgio Nunes","raw_affiliation_strings":["Universidade do Porto, Porto, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade do Porto, Porto, Portugal","institution_ids":["https://openalex.org/I182534213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8647,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.9047164,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"128","last_page":"139"},"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":9.999999747378752e-05,"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/T12488","display_name":"Mental Health via Writing","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/data-merging","display_name":"data merging","score":0.7350000143051147},{"id":"https://openalex.org/keywords/social-media-text","display_name":"social media text","score":0.6190000176429749},{"id":"https://openalex.org/keywords/facebook","display_name":"Facebook","score":0.3619999885559082},{"id":"https://openalex.org/keywords/english-text-classification","display_name":"English text classification","score":0.45399999618530273},{"id":"https://openalex.org/keywords/model-generalization","display_name":"model generalization","score":0.5649999976158142},{"id":"https://openalex.org/keywords/part-of-speech-features","display_name":"part-of-speech features","score":0.7260000109672546},{"id":"https://openalex.org/keywords/sentiment-features","display_name":"sentiment features","score":0.8009999990463257},{"id":"https://openalex.org/keywords/extreme-gradient-boosting","display_name":"extreme gradient boosting","score":0.5580000281333923},{"id":"https://openalex.org/keywords/random-forest","display_name":"random forest","score":0.7110000252723694},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"multilayer perceptron","score":0.8309999704360962}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7712947130203247},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6295117139816284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.617348849773407},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.612358808517456},{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.5583484172821045},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.5485086441040039},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.539642870426178},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.5379842519760132},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.5266076326370239},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5108901858329773},{"id":"https://openalex.org/C70153297","wikidata":"https://www.wikidata.org/wiki/Q5591907","display_name":"Gradient boosting","level":3,"score":0.49375972151756287},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4698423743247986},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.4425068795681},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.4355999827384949},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37752723693847656},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2250746488571167},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.21001917123794556},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.10053199529647827},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2913044599","doi":null,"is_oa":false,"landing_page_url":"https://www.aclweb.org/anthology/W18-4416.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419219","display_name":"International Conference on Computational Linguistics","issn_l":"1525-2477","issn":["1525-2477"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Computational Linguistics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W46659105","https://openalex.org/W78136081","https://openalex.org/W80056832","https://openalex.org/W346733163","https://openalex.org/W1071251684","https://openalex.org/W1724486527","https://openalex.org/W1861103856","https://openalex.org/W1965155572","https://openalex.org/W2029558656","https://openalex.org/W2037781503","https://openalex.org/W2091190355","https://openalex.org/W2098834812","https://openalex.org/W2099813784","https://openalex.org/W2156202195","https://openalex.org/W2156580264","https://openalex.org/W2164628858","https://openalex.org/W2181854537","https://openalex.org/W2209227144","https://openalex.org/W2295216512","https://openalex.org/W2311430799","https://openalex.org/W2340954483","https://openalex.org/W2399587463","https://openalex.org/W2465011684","https://openalex.org/W2473555522","https://openalex.org/W2537985163","https://openalex.org/W2564933006","https://openalex.org/W2580301823","https://openalex.org/W2585712495","https://openalex.org/W2595653137","https://openalex.org/W2604821579","https://openalex.org/W2612950887","https://openalex.org/W2613977835","https://openalex.org/W2620540598","https://openalex.org/W2740168486","https://openalex.org/W2773126195","https://openalex.org/W2794988414","https://openalex.org/W2912102236"],"related_works":["https://openalex.org/W2914491155","https://openalex.org/W2912102236","https://openalex.org/W2913474415","https://openalex.org/W2907973983","https://openalex.org/W2997575635","https://openalex.org/W2895645998","https://openalex.org/W2914034656","https://openalex.org/W3153055731","https://openalex.org/W2912123473","https://openalex.org/W4405248513"],"abstract_inverted_index":{"This":[0,29],"paper":[1],"presents":[2],"the":[3,6,10,17,34,41,110,131,143],"approach":[4,52],"of":[5,36,43,66,74,145],"team":[7],"\u201cgroutar\u201d":[8],"to":[9,32,96,112,118],"shared":[11],"task":[12],"on":[13],"Aggression":[14],"Identification,":[15],"considering":[16],"test":[18,33],"sets":[19],"in":[20,40,142,159],"English,":[21],"both":[22,160],"from":[23,120,152],"Facebook":[24,161],"and":[25,56,59,70,87,115,130,162],"general":[26],"Social":[27,163],"Media.":[28],"experiment":[30],"aims":[31],"effect":[35],"merging":[37],"new":[38],"datasets":[39,98],"performance":[42],"classification":[44,101,144],"models.":[45],"We":[46],"followed":[47],"a":[48],"standard":[49],"machine":[50],"learning":[51],"with":[53,78,136],"training,":[54],"validation,":[55],"testing":[57],"phases,":[58],"considered":[60],"features":[61],"such":[62],"as":[63],"part-of-speech,":[64],"frequencies":[65],"insults,":[67],"punctuation,":[68],"sentiment,":[69],"capitalization.":[71],"In":[72],"terms":[73],"algorithms,":[75],"we":[76,126],"experimented":[77],"Boosted":[79],"Logistic":[80],"Regression,":[81],"Multi-Layer":[82],"Perceptron,":[83],"Parallel":[84],"Random":[85],"Forest":[86],"eXtreme":[88],"Gradient":[89],"Boosting.":[90],"One":[91],"question":[92],"appearing":[93],"was":[94],"how":[95],"merge":[97],"using":[99],"different":[100,121,153],"systems":[102],"(e.g.":[103],"aggression":[104],"vs.":[105],"toxicity).":[106],"Other":[107],"issue":[108],"concerns":[109],"possibility":[111],"generalize":[113],"models":[114,169],"apply":[116],"them":[117],"data":[119,138,151],"social":[122,146],"networks.":[123],"Regarding":[124],"these,":[125],"merged":[127],"two":[128],"datasets,":[129],"results":[132,158],"showed":[133],"that":[134,166],"training":[135],"similar":[137],"is":[139],"an":[140,172],"advantage":[141],"networks":[147],"data.":[148],"However,":[149],"adding":[150],"platforms,":[154],"allowed":[155],"slightly":[156],"better":[157],"Media,":[164],"indicating":[165],"more":[167],"generalized":[168],"can":[170],"be":[171],"advantage.":[173]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":8}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2019-02-21T00:00:00"}