{"id":"https://openalex.org/W2612449475","doi":"https://doi.org/10.1109/ictas.2017.7920659","title":"Semi-supervised probabilistics approach for normalising informal short text messages","display_name":"Semi-supervised probabilistics approach for normalising informal short text messages","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2612449475","doi":"https://doi.org/10.1109/ictas.2017.7920659","mag":"2612449475"},"language":"en","primary_location":{"id":"doi:10.1109/ictas.2017.7920659","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictas.2017.7920659","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Conference on Information Communication Technology and Society (ICTAS)","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/A5042301177","display_name":"Abiodun Modupe","orcid":"https://orcid.org/0000-0002-9732-6466"},"institutions":[{"id":"https://openalex.org/I192619145","display_name":"University of the Witwatersrand","ror":"https://ror.org/03rp50x72","country_code":"ZA","type":"education","lineage":["https://openalex.org/I192619145"]}],"countries":["ZA"],"is_corresponding":true,"raw_author_name":"Abiodun Modupe","raw_affiliation_strings":["School of Computer Science and Applied Mathematics, University of the Witwatersrand, Johannesburg, South Africa"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Applied Mathematics, University of the Witwatersrand, Johannesburg, South Africa","institution_ids":["https://openalex.org/I192619145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049945687","display_name":"Turgay \u00c7elik","orcid":"https://orcid.org/0000-0001-6925-6010"},"institutions":[{"id":"https://openalex.org/I192619145","display_name":"University of the Witwatersrand","ror":"https://ror.org/03rp50x72","country_code":"ZA","type":"education","lineage":["https://openalex.org/I192619145"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Turgay Celik","raw_affiliation_strings":["School of Computer Science and Applied Mathematics, University of the Witwatersrand, Johannesburg, South Africa"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Applied Mathematics, University of the Witwatersrand, Johannesburg, South Africa","institution_ids":["https://openalex.org/I192619145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060690192","display_name":"Vukosi Marivate","orcid":"https://orcid.org/0000-0002-6731-6267"},"institutions":[{"id":"https://openalex.org/I21360634","display_name":"Council for Scientific and Industrial Research","ror":"https://ror.org/05j00sr48","country_code":"ZA","type":"funder","lineage":["https://openalex.org/I21360634"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Vukosi Marivate","raw_affiliation_strings":["Council for Scientific and Industrial Research (CSIR), Modelling and Digital Science, Pretoria, South Africa"],"affiliations":[{"raw_affiliation_string":"Council for Scientific and Industrial Research (CSIR), Modelling and Digital Science, Pretoria, South Africa","institution_ids":["https://openalex.org/I21360634"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082730857","display_name":"Melvin Diale","orcid":null},"institutions":[{"id":"https://openalex.org/I21360634","display_name":"Council for Scientific and Industrial Research","ror":"https://ror.org/05j00sr48","country_code":"ZA","type":"funder","lineage":["https://openalex.org/I21360634"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Melvin Diale","raw_affiliation_strings":["Council for Scientific and Industrial Research (CSIR), Modelling and Digital Science, Pretoria, South Africa"],"affiliations":[{"raw_affiliation_string":"Council for Scientific and Industrial Research (CSIR), Modelling and Digital Science, Pretoria, South Africa","institution_ids":["https://openalex.org/I21360634"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5042301177"],"corresponding_institution_ids":["https://openalex.org/I192619145"],"apc_list":null,"apc_paid":null,"fwci":0.9751,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.8147611,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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/T10028","display_name":"Topic Modeling","score":0.998199999332428,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9958999752998352,"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":0.8148626089096069},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6704397201538086},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6346129775047302},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5907639861106873},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5826027989387512},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5737344026565552},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49852776527404785},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.4964938759803772},{"id":"https://openalex.org/keywords/word2vec","display_name":"Word2vec","score":0.45592713356018066},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17700797319412231},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10700404644012451}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8148626089096069},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6704397201538086},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6346129775047302},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5907639861106873},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5826027989387512},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5737344026565552},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49852776527404785},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.4964938759803772},{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.45592713356018066},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17700797319412231},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10700404644012451},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ictas.2017.7920659","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictas.2017.7920659","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Conference on Information Communication Technology and Society (ICTAS)","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":0,"referenced_works":[],"related_works":["https://openalex.org/W2980729574","https://openalex.org/W1560851690","https://openalex.org/W3092047717","https://openalex.org/W4390881630","https://openalex.org/W2905749112","https://openalex.org/W2346530426","https://openalex.org/W3099354896","https://openalex.org/W4287599800","https://openalex.org/W4312264180","https://openalex.org/W3046869600"],"abstract_inverted_index":{"The":[0,106],"growing":[1],"use":[2],"of":[3,12,16,21,108],"informal":[4,132],"social":[5,156],"text":[6,57],"messages":[7,22],"on":[8,138],"Twitter":[9],"is":[10,49,67,147],"one":[11],"the":[13,55,64,80,88,125,145],"known":[14],"sources":[15],"big":[17],"data.":[18],"These":[19],"type":[20],"are":[23,111],"noisy":[24],"and":[25,33,58,84,102,144],"frequently":[26],"rife":[27],"with":[28,91],"acronyms,":[29],"slangs,":[30],"grammatical":[31],"errors":[32],"non-standard":[34,52],"words":[35,53,152],"causing":[36],"grief":[37],"for":[38,98,129],"natural":[39],"language":[40,75],"processing":[41],"(NLP)":[42],"techniques.":[43],"In":[44],"this":[45],"study,":[46],"our":[47],"contribution":[48],"to":[50,62,69,78,95,123,149],"target":[51],"in":[54,153],"short":[56,133],"propose":[59],"a":[60,92,130,139],"method":[61,73],"which":[63],"given":[65,131],"word":[66],"likely":[68],"be":[70],"transformed.":[71],"Our":[72],"uses":[74],"model":[76,94],"probability":[77],"characterise":[79],"relationship":[81],"between":[82],"formal":[83],"Informal-word,":[85],"then":[86],"employ":[87],"string":[89],"similarity":[90],"log-linear":[93],"includes":[96],"features":[97,110],"both":[99],"word-level":[100],"transformation":[101],"local":[103],"context":[104],"similarity.":[105],"weights":[107],"these":[109],"trained":[112],"by":[113],"employing":[114],"maximum":[115],"likelihood":[116],"framework":[117],"using":[118],"stochastic":[119],"gradient":[120],"descent":[121],"(SGD)":[122],"hypothesise":[124],"better":[126],"clean":[127],"feature":[128],"text.":[134],"Experiments":[135],"were":[136],"conducted":[137],"publicly":[140],"available":[141],"Enlish-language":[142],"tweet":[143],"approach":[146],"able":[148],"normalise":[150],"inflected":[151],"an":[154],"online":[155],"network.":[157]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}