{"id":"https://openalex.org/W2554522938","doi":"https://doi.org/10.5220/0006083004130418","title":"Evaluation of Statistical Text Normalisation Techniques for Twitter","display_name":"Evaluation of Statistical Text Normalisation Techniques for Twitter","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2554522938","doi":"https://doi.org/10.5220/0006083004130418","mag":"2554522938"},"language":"en","primary_location":{"id":"doi:10.5220/0006083004130418","is_oa":false,"landing_page_url":"https://doi.org/10.5220/0006083004130418","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10292/12019","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018429723","display_name":"Phavanh Sosamphan","orcid":null},"institutions":[{"id":"https://openalex.org/I872614749","display_name":"Unitec Institute of Technology","ror":"https://ror.org/01px84952","country_code":"NZ","type":"education","lineage":["https://openalex.org/I4387152882","https://openalex.org/I872614749"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Phavanh Sosamphan","raw_affiliation_strings":["Unitec Institute of Technology, New Zealand","Department of Computer Science, Unitec Institute of Technology, Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Unitec Institute of Technology, New Zealand","institution_ids":["https://openalex.org/I872614749"]},{"raw_affiliation_string":"Department of Computer Science, Unitec Institute of Technology, Auckland, New Zealand","institution_ids":["https://openalex.org/I872614749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035576142","display_name":"Veronica Liesaputra","orcid":"https://orcid.org/0000-0001-5793-833X"},"institutions":[{"id":"https://openalex.org/I872614749","display_name":"Unitec Institute of Technology","ror":"https://ror.org/01px84952","country_code":"NZ","type":"education","lineage":["https://openalex.org/I4387152882","https://openalex.org/I872614749"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Veronica Liesaputra","raw_affiliation_strings":["Unitec Institute of Technology, New Zealand","Department of Computer Science, Unitec Institute of Technology, Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Unitec Institute of Technology, New Zealand","institution_ids":["https://openalex.org/I872614749"]},{"raw_affiliation_string":"Department of Computer Science, Unitec Institute of Technology, Auckland, New Zealand","institution_ids":["https://openalex.org/I872614749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082853606","display_name":"Sira Yongchareon","orcid":"https://orcid.org/0000-0002-2880-6618"},"institutions":[{"id":"https://openalex.org/I39854758","display_name":"Auckland University of Technology","ror":"https://ror.org/01zvqw119","country_code":"NZ","type":"education","lineage":["https://openalex.org/I39854758"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Sira Yongchareon","raw_affiliation_strings":["AUT, New Zealand","Department of Information Technology & Software Engineering, AUT, Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AUT, New Zealand","institution_ids":["https://openalex.org/I39854758"]},{"raw_affiliation_string":"Department of Information Technology & Software Engineering, AUT, Auckland, New Zealand","institution_ids":["https://openalex.org/I39854758"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075471089","display_name":"Mahsa Mohaghegh","orcid":"https://orcid.org/0000-0003-2228-8300"},"institutions":[{"id":"https://openalex.org/I872614749","display_name":"Unitec Institute of Technology","ror":"https://ror.org/01px84952","country_code":"NZ","type":"education","lineage":["https://openalex.org/I4387152882","https://openalex.org/I872614749"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Mahsa Mohaghegh","raw_affiliation_strings":["Unitec Institute of Technology, New Zealand","Department of Computer Science, Unitec Institute of Technology, Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Unitec Institute of Technology, New Zealand","institution_ids":["https://openalex.org/I872614749"]},{"raw_affiliation_string":"Department of Computer Science, Unitec Institute of Technology, Auckland, New Zealand","institution_ids":["https://openalex.org/I872614749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.0810567,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"413","last_page":"418"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9976999759674072,"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":0.8130423426628113},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.642052948474884},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.59799724817276},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.58608078956604},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5727035999298096},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5343524217605591},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.515294075012207},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.45946642756462097},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3561673164367676},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08575135469436646},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06857320666313171}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8130423426628113},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.642052948474884},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.59799724817276},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.58608078956604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5727035999298096},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5343524217605591},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.515294075012207},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.45946642756462097},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3561673164367676},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08575135469436646},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06857320666313171},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.5220/0006083004130418","is_oa":false,"landing_page_url":"https://doi.org/10.5220/0006083004130418","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:aut.researchgateway.ac.nz:10292/12019","is_oa":true,"landing_page_url":"http://hdl.handle.net/10292/12019","pdf_url":null,"source":{"id":"https://openalex.org/S4406922880","display_name":"AUT Scholarly Commons","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Contribution"},{"id":"pmh:oai:openrepository.aut.ac.nz:10292/12019","is_oa":true,"landing_page_url":"https://hdl.handle.net/10292/12019","pdf_url":null,"source":{"id":"https://openalex.org/S4306401809","display_name":"Tuwhera (Auckland University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I39854758","host_organization_name":"Auckland University of Technology","host_organization_lineage":["https://openalex.org/I39854758"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Contribution"},{"id":"pmh:oai:researchbank.ac.nz:10652/3808","is_oa":false,"landing_page_url":"https://hdl.handle.net/10652/3808","pdf_url":null,"source":{"id":"https://openalex.org/S4306401628","display_name":"Unitec Research Bank (Unitec Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I872614749","host_organization_name":"Unitec Institute of Technology","host_organization_lineage":["https://openalex.org/I872614749"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:aut.researchgateway.ac.nz:10292/12019","is_oa":true,"landing_page_url":"http://hdl.handle.net/10292/12019","pdf_url":null,"source":{"id":"https://openalex.org/S4406922880","display_name":"AUT Scholarly Commons","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Contribution"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8600000143051147,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W605135440","https://openalex.org/W632291594","https://openalex.org/W1631260214","https://openalex.org/W1868971014","https://openalex.org/W2016443085","https://openalex.org/W2059067870","https://openalex.org/W2108082276","https://openalex.org/W2397927934"],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2913146933","https://openalex.org/W2372385138","https://openalex.org/W4296359239","https://openalex.org/W2101155126","https://openalex.org/W4251972423","https://openalex.org/W2944691285"],"abstract_inverted_index":{"One":[0],"of":[1,8,19,149],"the":[2,6,16,101,111,127,135,155],"major":[3],"challenges":[4],"in":[5,34,97,134],"era":[7],"big":[9],"data":[10],"use":[11],"is":[12],"how":[13],"to":[14,50,66,86,99],"'clean'":[15],"vast":[17],"amount":[18],"data,":[20],"particularly":[21],"from":[22],"micro-blog":[23],"websites":[24],"like":[25],"Twitter.":[26],"Twitter":[27,124],"messages,":[28],"called":[29],"tweets,":[30],"are":[31,61,151],"commonly":[32],"written":[33],"ill-forms,":[35],"including":[36],"abbreviations,":[37,115],"repeated":[38,116],"characters,":[39],"and":[40,52,76,93,118,141],"misspelled":[41,119],"words.":[42,120],"These":[43],"'noisy":[44],"tweets'":[45],"require":[46],"text":[47],"normalisation":[48,91],"techniques":[49,64],"detect":[51],"convert":[53],"them":[54],"into":[55],"more":[56],"accurate":[57],"English":[58],"sentences.":[59],"There":[60],"several":[62],"existing":[63,89],"proposed":[65],"solve":[67],"these":[68],"issues,":[69],"however":[70],"each":[71],"technique":[72],"possess":[73],"some":[74],"limitations":[75],"therefore":[77],"cannot":[78],"achieve":[79,131],"good":[80],"overall":[81],"results.":[82],"This":[83],"paper":[84],"aims":[85],"evaluate":[87],"individual":[88],"statistical":[90],"methods":[92],"their":[94],"possible":[95],"combinations":[96],"order":[98],"find":[100],"best":[102,128],"combination":[103,129],"that":[104],"can":[105,130],"efficiently":[106],"clean":[107],"noisy":[108],"tweets":[109],"at":[110],"character-level,":[112],"which":[113,150],"contains":[114],"letters":[117],"Tested":[121],"on":[122],"our":[123],"sample":[125],"dataset,":[126],"88%":[132],"accuracy":[133],"Bilingual":[136],"Evaluation":[137],"Understudy":[138],"(BLEU)":[139],"score":[140],"7%":[142],"Word":[143],"Error":[144],"Rate":[145],"(WER)":[146],"score,":[147],"both":[148],"considered":[152],"better":[153],"than":[154],"baseline":[156],"model.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2016-11-30T00:00:00"}