{"id":"https://openalex.org/W2016443085","doi":"https://doi.org/10.1145/2414425.2414430","title":"Lexical normalization for social media text","display_name":"Lexical normalization for social media text","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W2016443085","doi":"https://doi.org/10.1145/2414425.2414430","mag":"2016443085"},"language":"en","primary_location":{"id":"doi:10.1145/2414425.2414430","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2414425.2414430","pdf_url":null,"source":{"id":"https://openalex.org/S2492086750","display_name":"ACM Transactions on Intelligent Systems and Technology","issn_l":"2157-6904","issn":["2157-6904","2157-6912"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Intelligent Systems and Technology","raw_type":"journal-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/A5047240103","display_name":"Bo Han","orcid":"https://orcid.org/0000-0002-6338-0958"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Bo Han","raw_affiliation_strings":["NICTA Victoria Research Laboratory and The University of Melbourne, Australia","NICTA Victoria Research Laboratory and The University of Melbourne, Australia#TAB#"],"affiliations":[{"raw_affiliation_string":"NICTA Victoria Research Laboratory and The University of Melbourne, Australia","institution_ids":["https://openalex.org/I42894916","https://openalex.org/I165779595"]},{"raw_affiliation_string":"NICTA Victoria Research Laboratory and The University of Melbourne, Australia#TAB#","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037912029","display_name":"Paul Cook","orcid":"https://orcid.org/0000-0001-7791-9072"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Paul Cook","raw_affiliation_strings":["The University of Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103085805","display_name":"Timothy Baldwin","orcid":"https://orcid.org/0000-0002-4445-1386"},"institutions":[{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Timothy Baldwin","raw_affiliation_strings":["NICTA Victoria Research Laboratory and The University of Melbourne, Australia","NICTA Victoria Research Laboratory and The University of Melbourne, Australia#TAB#"],"affiliations":[{"raw_affiliation_string":"NICTA Victoria Research Laboratory and The University of Melbourne, Australia","institution_ids":["https://openalex.org/I42894916","https://openalex.org/I165779595"]},{"raw_affiliation_string":"NICTA Victoria Research Laboratory and The University of Melbourne, Australia#TAB#","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5047240103"],"corresponding_institution_ids":["https://openalex.org/I165779595","https://openalex.org/I42894916"],"apc_list":null,"apc_paid":null,"fwci":30.6431,"has_fulltext":false,"cited_by_count":188,"citation_normalized_percentile":{"value":0.99684661,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"4","issue":"1","first_page":"1","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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":0.996999979019165,"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":0.9044939875602722},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7158783078193665},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6857655644416809},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6191171407699585},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6067715287208557},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5641191005706787},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.503060519695282},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.4761631190776825},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.45459818840026855},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.41452154517173767},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3451162576675415},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.11487022042274475},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09863090515136719}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9044939875602722},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7158783078193665},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6857655644416809},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6191171407699585},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6067715287208557},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5641191005706787},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.503060519695282},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.4761631190776825},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.45459818840026855},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.41452154517173767},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3451162576675415},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.11487022042274475},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09863090515136719},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2414425.2414430","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2414425.2414430","pdf_url":null,"source":{"id":"https://openalex.org/S2492086750","display_name":"ACM Transactions on Intelligent Systems and Technology","issn_l":"2157-6904","issn":["2157-6904","2157-6912"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Intelligent Systems and Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W4538592","https://openalex.org/W11244355","https://openalex.org/W63056884","https://openalex.org/W157541337","https://openalex.org/W1480643256","https://openalex.org/W1490960179","https://openalex.org/W1502364498","https://openalex.org/W1508977358","https://openalex.org/W1520449809","https://openalex.org/W1524281572","https://openalex.org/W1586073462","https://openalex.org/W1607035479","https://openalex.org/W1631260214","https://openalex.org/W1647671624","https://openalex.org/W1868971014","https://openalex.org/W1901600440","https://openalex.org/W1965555277","https://openalex.org/W1995875735","https://openalex.org/W1996430422","https://openalex.org/W2057399676","https://openalex.org/W2057900969","https://openalex.org/W2069870183","https://openalex.org/W2096438711","https://openalex.org/W2101105183","https://openalex.org/W2101200183","https://openalex.org/W2111192396","https://openalex.org/W2113125055","https://openalex.org/W2114210953","https://openalex.org/W2118585731","https://openalex.org/W2119759918","https://openalex.org/W2120874923","https://openalex.org/W2124499489","https://openalex.org/W2125838338","https://openalex.org/W2129271949","https://openalex.org/W2133503566","https://openalex.org/W2144226312","https://openalex.org/W2146867136","https://openalex.org/W2146950091","https://openalex.org/W2147880316","https://openalex.org/W2152336115","https://openalex.org/W2153848201","https://openalex.org/W2157765050","https://openalex.org/W2163942301","https://openalex.org/W2164107060","https://openalex.org/W2166776180","https://openalex.org/W2167072947","https://openalex.org/W2172112754","https://openalex.org/W2250185284","https://openalex.org/W2290683883","https://openalex.org/W2499585162","https://openalex.org/W2524182563","https://openalex.org/W2597684388","https://openalex.org/W2912218307","https://openalex.org/W2913048852","https://openalex.org/W2913668833","https://openalex.org/W2914314925","https://openalex.org/W3001645704","https://openalex.org/W4206070857","https://openalex.org/W4237040408","https://openalex.org/W4242903024","https://openalex.org/W4285719527","https://openalex.org/W6600280466","https://openalex.org/W6631166905","https://openalex.org/W6636811518"],"related_works":["https://openalex.org/W4386014872","https://openalex.org/W1847536016","https://openalex.org/W4361193986","https://openalex.org/W3149094754","https://openalex.org/W2148703997","https://openalex.org/W4366851046","https://openalex.org/W3172681236","https://openalex.org/W2591697403","https://openalex.org/W2033371749","https://openalex.org/W1997182898"],"abstract_inverted_index":{"Twitter":[0],"provides":[1],"access":[2],"to":[3,46,66],"large":[4],"volumes":[5],"of":[6],"data":[7],"in":[8,27],"real":[9],"time,":[10],"but":[11],"is":[12],"notoriously":[13],"noisy,":[14],"hampering":[15],"its":[16],"utility":[17],"for":[18,35,73],"NLP.":[19],"In":[20],"this":[21],"article,":[22],"we":[23],"target":[24],"out-of-vocabulary":[25],"words":[26],"short":[28],"text":[29],"messages":[30],"and":[31,37,50,61,83,91],"propose":[32],"a":[33,44,92],"method":[34,42,78],"identifying":[36],"normalizing":[38],"lexical":[39,48],"variants.":[40],"Our":[41],"uses":[43],"classifier":[45],"detect":[47],"variants,":[49],"generates":[51],"correction":[52,71],"candidates":[53],"based":[54,95],"on":[55,96],"morphophonemic":[56],"similarity.":[57],"Both":[58],"word":[59],"similarity":[60],"context":[62],"are":[63],"then":[64],"exploited":[65],"select":[67],"the":[68,74],"most":[69],"probable":[70],"candidate":[72],"word.":[75],"The":[76],"proposed":[77],"doesn't":[79],"require":[80],"any":[81],"annotations,":[82],"achieves":[84],"state-of-the-art":[85],"performance":[86],"over":[87],"an":[88],"SMS":[89],"corpus":[90],"novel":[93],"dataset":[94],"Twitter.":[97]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":26},{"year":2019,"cited_by_count":21},{"year":2018,"cited_by_count":15},{"year":2017,"cited_by_count":18},{"year":2016,"cited_by_count":20},{"year":2015,"cited_by_count":18},{"year":2014,"cited_by_count":15},{"year":2013,"cited_by_count":9}],"updated_date":"2026-04-11T08:14:18.477133","created_date":"2025-10-10T00:00:00"}