{"id":"https://openalex.org/W3095278059","doi":"https://doi.org/10.1007/s11042-020-10082-6","title":"A survey of pre-processing techniques to improve short-text quality: a case study on hate speech detection on twitter","display_name":"A survey of pre-processing techniques to improve short-text quality: a case study on hate speech detection on twitter","publication_year":2020,"publication_date":"2020-11-04","ids":{"openalex":"https://openalex.org/W3095278059","doi":"https://doi.org/10.1007/s11042-020-10082-6","mag":"3095278059"},"language":"en","primary_location":{"id":"doi:10.1007/s11042-020-10082-6","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11042-020-10082-6","pdf_url":null,"source":{"id":"https://openalex.org/S110206669","display_name":"Multimedia Tools and Applications","issn_l":"1380-7501","issn":["1380-7501","1573-7721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimedia Tools and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/journal_contribution/A_survey_of_pre-processing_techniques_to_improve_short-text_quality_a_case_study_on_hate_speech_detection_on_twitter/20684002","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077006200","display_name":"Usman Naseem","orcid":"https://orcid.org/0000-0003-0191-7171"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Usman Naseem","raw_affiliation_strings":["University of Sydney, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"University of Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033585021","display_name":"Imran Razzak","orcid":"https://orcid.org/0000-0002-3930-6600"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Imran Razzak","raw_affiliation_strings":["Deakin University, Geelong, Australia"],"affiliations":[{"raw_affiliation_string":"Deakin University, Geelong, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071084001","display_name":"Peter Eklund","orcid":"https://orcid.org/0000-0003-2313-8603"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Peter W. Eklund","raw_affiliation_strings":["Deakin University, Geelong, Australia"],"affiliations":[{"raw_affiliation_string":"Deakin University, Geelong, Australia","institution_ids":["https://openalex.org/I149704539"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5077006200"],"corresponding_institution_ids":["https://openalex.org/I129604602"],"apc_list":null,"apc_paid":null,"fwci":10.0586,"has_fulltext":false,"cited_by_count":115,"citation_normalized_percentile":{"value":0.98548645,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"80","issue":"28-29","first_page":"35239","last_page":"35266"},"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/T11644","display_name":"Spam and Phishing Detection","score":0.9991999864578247,"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":0.9937999844551086,"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/computer-science","display_name":"Computer science","score":0.9038732051849365},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5465642213821411},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5425208210945129},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5127742886543274},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48266342282295227},{"id":"https://openalex.org/keywords/text-processing","display_name":"Text processing","score":0.4779379665851593},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4661102890968323},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.44358912110328674},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.44192183017730713},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4396674633026123},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3988815248012543},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33991408348083496}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9038732051849365},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5465642213821411},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5425208210945129},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5127742886543274},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48266342282295227},{"id":"https://openalex.org/C2779500292","wikidata":"https://www.wikidata.org/wiki/Q14802672","display_name":"Text processing","level":2,"score":0.4779379665851593},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4661102890968323},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.44358912110328674},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.44192183017730713},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4396674633026123},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3988815248012543},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33991408348083496},{"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s11042-020-10082-6","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11042-020-10082-6","pdf_url":null,"source":{"id":"https://openalex.org/S110206669","display_name":"Multimedia Tools and Applications","issn_l":"1380-7501","issn":["1380-7501","1573-7721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimedia Tools and Applications","raw_type":"journal-article"},{"id":"pmh:oai:dro.deakin.edu.au:DU:30145242","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401102","display_name":"Own your potential (DEAKIN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149704539","host_organization_name":"Deakin University","host_organization_lineage":["https://openalex.org/I149704539"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"},{"id":"pmh:oai:figshare.com:article/20684002","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/A_survey_of_pre-processing_techniques_to_improve_short-text_quality_a_case_study_on_hate_speech_detection_on_twitter/20684002","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/20684002","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/A_survey_of_pre-processing_techniques_to_improve_short-text_quality_a_case_study_on_hate_speech_detection_on_twitter/20684002","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W15334911","https://openalex.org/W1589554437","https://openalex.org/W1743243001","https://openalex.org/W1832693441","https://openalex.org/W1853454069","https://openalex.org/W1887786044","https://openalex.org/W1978394996","https://openalex.org/W2014545475","https://openalex.org/W2043870592","https://openalex.org/W2049434052","https://openalex.org/W2057308560","https://openalex.org/W2073254505","https://openalex.org/W2108420397","https://openalex.org/W2149233311","https://openalex.org/W2156413587","https://openalex.org/W2156741031","https://openalex.org/W2157765050","https://openalex.org/W2250539671","https://openalex.org/W2250999864","https://openalex.org/W2252215182","https://openalex.org/W2267835966","https://openalex.org/W2387314750","https://openalex.org/W2473555522","https://openalex.org/W2512317583","https://openalex.org/W2586850891","https://openalex.org/W2590061102","https://openalex.org/W2595653137","https://openalex.org/W2626126425","https://openalex.org/W2734862619","https://openalex.org/W2781487490","https://openalex.org/W2808079449","https://openalex.org/W2809205326","https://openalex.org/W2932321119","https://openalex.org/W2947680394","https://openalex.org/W2951876369","https://openalex.org/W2953479706","https://openalex.org/W2962963628","https://openalex.org/W2963355447","https://openalex.org/W2990453928","https://openalex.org/W3003958081","https://openalex.org/W3007443784","https://openalex.org/W3015255253","https://openalex.org/W3015435341","https://openalex.org/W3022029496","https://openalex.org/W3039554467","https://openalex.org/W3090245549","https://openalex.org/W3091311542","https://openalex.org/W4233787372"],"related_works":["https://openalex.org/W2804364458","https://openalex.org/W4298130764","https://openalex.org/W2132641928","https://openalex.org/W2090259340","https://openalex.org/W4310225030","https://openalex.org/W1964658544","https://openalex.org/W254547640","https://openalex.org/W2978665856","https://openalex.org/W2892088913","https://openalex.org/W2176632294"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":24},{"year":2023,"cited_by_count":34},{"year":2022,"cited_by_count":25},{"year":2021,"cited_by_count":15}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
