{"id":"https://openalex.org/W2983418531","doi":"https://doi.org/10.18653/v1/d19-5554","title":"Normalization of Indonesian-English Code-Mixed Twitter Data","display_name":"Normalization of Indonesian-English Code-Mixed Twitter Data","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2983418531","doi":"https://doi.org/10.18653/v1/d19-5554","mag":"2983418531"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d19-5554","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-5554","pdf_url":"https://www.aclweb.org/anthology/D19-5554.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D19-5554.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007981056","display_name":"Anab Maulana Barik","orcid":null},"institutions":[{"id":"https://openalex.org/I29617571","display_name":"University of Indonesia","ror":"https://ror.org/0116zj450","country_code":"ID","type":"education","lineage":["https://openalex.org/I29617571"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Anab Maulana Barik","raw_affiliation_strings":["Faculty of Computer Science, Universitas Indonesia Depok, Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science, Universitas Indonesia Depok, Indonesia","institution_ids":["https://openalex.org/I29617571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054993995","display_name":"Rahmad Mahendra","orcid":"https://orcid.org/0000-0003-1107-7073"},"institutions":[{"id":"https://openalex.org/I29617571","display_name":"University of Indonesia","ror":"https://ror.org/0116zj450","country_code":"ID","type":"education","lineage":["https://openalex.org/I29617571"]}],"countries":["ID"],"is_corresponding":true,"raw_author_name":"Rahmad Mahendra","raw_affiliation_strings":["Faculty of Computer Science, Universitas Indonesia Depok, Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science, Universitas Indonesia Depok, Indonesia","institution_ids":["https://openalex.org/I29617571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052754690","display_name":"Mirna Adriani","orcid":null},"institutions":[{"id":"https://openalex.org/I29617571","display_name":"University of Indonesia","ror":"https://ror.org/0116zj450","country_code":"ID","type":"education","lineage":["https://openalex.org/I29617571"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Mirna Adriani","raw_affiliation_strings":["Faculty of Computer Science, Universitas Indonesia Depok, Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science, Universitas Indonesia Depok, Indonesia","institution_ids":["https://openalex.org/I29617571"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5054993995"],"corresponding_institution_ids":["https://openalex.org/I29617571"],"apc_list":null,"apc_paid":null,"fwci":3.6272,"has_fulltext":true,"cited_by_count":45,"citation_normalized_percentile":{"value":0.94500288,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"417","last_page":"424"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9853000044822693,"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":0.843395471572876},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6649254560470581},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.656257152557373},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.5620833039283752},{"id":"https://openalex.org/keywords/indonesian","display_name":"Indonesian","score":0.5441951751708984},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5369453430175781},{"id":"https://openalex.org/keywords/code-switching","display_name":"Code-switching","score":0.49153169989585876},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.47342947125434875},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4179905354976654},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3248956501483917},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2603946328163147},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.2586970925331116}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.843395471572876},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6649254560470581},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.656257152557373},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.5620833039283752},{"id":"https://openalex.org/C2779207338","wikidata":"https://www.wikidata.org/wiki/Q9240","display_name":"Indonesian","level":2,"score":0.5441951751708984},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5369453430175781},{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.49153169989585876},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.47342947125434875},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4179905354976654},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3248956501483917},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2603946328163147},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2586970925331116},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d19-5554","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-5554","pdf_url":"https://www.aclweb.org/anthology/D19-5554.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d19-5554","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-5554","pdf_url":"https://www.aclweb.org/anthology/D19-5554.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8299999833106995,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320323819","display_name":"Universitas Indonesia","ror":"https://ror.org/0116zj450"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2983418531.pdf","grobid_xml":"https://content.openalex.org/works/W2983418531.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1497763703","https://openalex.org/W1623072288","https://openalex.org/W2014962660","https://openalex.org/W2096438711","https://openalex.org/W2112255502","https://openalex.org/W2146277089","https://openalex.org/W2153579005","https://openalex.org/W2250660051","https://openalex.org/W2251237590","https://openalex.org/W2462558730","https://openalex.org/W2763882345","https://openalex.org/W2795670164","https://openalex.org/W2885940157","https://openalex.org/W2963285772","https://openalex.org/W3088665616","https://openalex.org/W4294170691","https://openalex.org/W4322019472"],"related_works":["https://openalex.org/W2771594921","https://openalex.org/W2432897346","https://openalex.org/W2181336723","https://openalex.org/W4389976243","https://openalex.org/W3158134258","https://openalex.org/W2151197196","https://openalex.org/W3045818198","https://openalex.org/W3034697300","https://openalex.org/W4287760117","https://openalex.org/W2355857108"],"abstract_inverted_index":{"Twitter":[0,80],"is":[1,26,49,106],"an":[2],"excellent":[3],"source":[4],"of":[5,16,58,93,112],"data":[6,115],"for":[7,31,116],"NLP":[8],"researches":[9],"as":[10,38,40],"it":[11],"offers":[12],"a":[13,89,109],"tremendous":[14],"amount":[15],"textual":[17],"data.":[18],"However,":[19],"processing":[20],"tweet":[21,55],"to":[22,107],"extract":[23],"meaningful":[24],"information":[25],"very":[27],"challenging,":[28],"at":[29],"least":[30],"two":[32],"reasons:":[33],"(i)":[34],"using":[35],"nonstandard":[36],"words":[37],"well":[39],"informal":[41],"writing":[42],"manner,":[43],"and":[44,102],"(ii)":[45],"code-mixing":[46],"issues,":[47],"which":[48],"combining":[50],"multiple":[51],"languages":[52],"in":[53,66,78,84],"single":[54],"conversation.":[56],"Most":[57],"the":[59],"previous":[60],"works":[61],"have":[62],"addressed":[63],"both":[64],"issues":[65],"isolated":[67],"different":[68],"task.":[69],"In":[70],"this":[71],"study,":[72],"we":[73],"work":[74],"on":[75],"normalization":[76],"task":[77],"code-mixed":[79,114],"data,":[81],"more":[82],"specifically":[83],"Indonesian-English":[85,113],"language.":[86],"We":[87],"propose":[88],"pipeline":[90],"that":[91],"consists":[92],"four":[94],"modules,":[95],"i.e":[96],"tokenization,":[97],"language":[98],"identification,":[99],"lexical":[100],"normalization,":[101],"translation.":[103],"Another":[104],"contribution":[105],"provide":[108],"gold":[110],"standard":[111],"each":[117],"module.":[118]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":4}],"updated_date":"2026-05-28T09:10:13.091523","created_date":"2025-10-10T00:00:00"}