{"id":"https://openalex.org/W2969270288","doi":"https://doi.org/10.3390/mti3030060","title":"Data-Driven Lexical Normalization for Medical SocialMedia","display_name":"Data-Driven Lexical Normalization for Medical SocialMedia","publication_year":2019,"publication_date":"2019-08-20","ids":{"openalex":"https://openalex.org/W2969270288","doi":"https://doi.org/10.3390/mti3030060","mag":"2969270288"},"language":"en","primary_location":{"id":"doi:10.3390/mti3030060","is_oa":true,"landing_page_url":"https://doi.org/10.3390/mti3030060","pdf_url":"https://www.mdpi.com/2414-4088/3/3/60/pdf?version=1568605799","source":{"id":"https://openalex.org/S4210226272","display_name":"Multimodal Technologies and Interaction","issn_l":"2414-4088","issn":["2414-4088"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimodal Technologies and Interaction","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2414-4088/3/3/60/pdf?version=1568605799","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012487697","display_name":"Anne Dirkson","orcid":"https://orcid.org/0000-0002-4332-0296"},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Anne Dirkson","raw_affiliation_strings":["Leiden Institute for Advanced Computer Science, Leiden University, 2333 CA Leiden, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Leiden Institute for Advanced Computer Science, Leiden University, 2333 CA Leiden, The Netherlands","institution_ids":["https://openalex.org/I121797337"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027124439","display_name":"Suzan Verberne","orcid":"https://orcid.org/0000-0002-9609-9505"},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Suzan Verberne","raw_affiliation_strings":["Leiden Institute for Advanced Computer Science, Leiden University, 2333 CA Leiden, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Leiden Institute for Advanced Computer Science, Leiden University, 2333 CA Leiden, The Netherlands","institution_ids":["https://openalex.org/I121797337"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086087170","display_name":"Abeed Sarker","orcid":"https://orcid.org/0000-0001-7358-544X"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abeed Sarker","raw_affiliation_strings":["Department of Biomedical Informatics, Emory University, Atlanta, GA 30322, USA"],"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Emory University, Atlanta, GA 30322, USA","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049624750","display_name":"Wessel Kraaij","orcid":"https://orcid.org/0000-0001-7797-619X"},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Wessel Kraaij","raw_affiliation_strings":["Leiden Institute for Advanced Computer Science, Leiden University, 2333 CA Leiden, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Leiden Institute for Advanced Computer Science, Leiden University, 2333 CA Leiden, The Netherlands","institution_ids":["https://openalex.org/I121797337"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5012487697"],"corresponding_institution_ids":["https://openalex.org/I121797337"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":0.8682,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.81024113,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"3","issue":"3","first_page":"60","last_page":"60"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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":0.9995999932289124,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9983000159263611,"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/spelling","display_name":"Spelling","score":0.9356667995452881},{"id":"https://openalex.org/keywords/mistake","display_name":"Mistake","score":0.8107485771179199},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7246333956718445},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7037767171859741},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6433724164962769},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.6260938048362732},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.5480020046234131},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5454197525978088},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3529708981513977},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.14175528287887573},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.06997755169868469}],"concepts":[{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.9356667995452881},{"id":"https://openalex.org/C2777179996","wikidata":"https://www.wikidata.org/wiki/Q911222","display_name":"Mistake","level":2,"score":0.8107485771179199},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7246333956718445},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7037767171859741},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6433724164962769},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.6260938048362732},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.5480020046234131},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5454197525978088},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3529708981513977},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.14175528287887573},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.06997755169868469},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3390/mti3030060","is_oa":true,"landing_page_url":"https://doi.org/10.3390/mti3030060","pdf_url":"https://www.mdpi.com/2414-4088/3/3/60/pdf?version=1568605799","source":{"id":"https://openalex.org/S4210226272","display_name":"Multimodal Technologies and Interaction","issn_l":"2414-4088","issn":["2414-4088"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimodal Technologies and Interaction","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:97866c664c4944b6b3234099971567e3","is_oa":true,"landing_page_url":"https://doaj.org/article/97866c664c4944b6b3234099971567e3","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Multimodal Technologies and Interaction, Vol 3, Iss 3, p 60 (2019)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2414-4088/3/3/60/","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3390/mti3030060","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"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":"Multimodal Technologies and Interaction","raw_type":"Text"},{"id":"pmh:oai:scholarlypublications.universiteitleiden.nl:item_2911319","is_oa":false,"landing_page_url":"https://hdl.handle.net/1887/77332","pdf_url":null,"source":{"id":"https://openalex.org/S4306400850","display_name":"Leiden Repository (Leiden University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I121797337","host_organization_name":"Leiden University","host_organization_lineage":["https://openalex.org/I121797337"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Multimodal Technologies and Interaction","raw_type":"Article / Letter to editor"},{"id":"pmh:ul:oai:scholarlypublications.universiteitleiden.nl:item_2911319","is_oa":true,"landing_page_url":"http://hdl.handle.net/1887/77332","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"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":"Multimodal Technologies and Interaction, 3(3), 60. MDPI","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.3390/mti3030060","is_oa":true,"landing_page_url":"https://doi.org/10.3390/mti3030060","pdf_url":"https://www.mdpi.com/2414-4088/3/3/60/pdf?version=1568605799","source":{"id":"https://openalex.org/S4210226272","display_name":"Multimodal Technologies and Interaction","issn_l":"2414-4088","issn":["2414-4088"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimodal Technologies and Interaction","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2969270288.pdf","grobid_xml":"https://content.openalex.org/works/W2969270288.grobid-xml"},"referenced_works_count":57,"referenced_works":["https://openalex.org/W17513810","https://openalex.org/W157541337","https://openalex.org/W1520449809","https://openalex.org/W1702375188","https://openalex.org/W1841433433","https://openalex.org/W1984291951","https://openalex.org/W1990755853","https://openalex.org/W1995875735","https://openalex.org/W2006642610","https://openalex.org/W2010595692","https://openalex.org/W2016443085","https://openalex.org/W2018616927","https://openalex.org/W2032355794","https://openalex.org/W2102742655","https://openalex.org/W2119224635","https://openalex.org/W2131546905","https://openalex.org/W2150102617","https://openalex.org/W2163542005","https://openalex.org/W2171469118","https://openalex.org/W2224826979","https://openalex.org/W2250409328","https://openalex.org/W2250475966","https://openalex.org/W2250660051","https://openalex.org/W2250729567","https://openalex.org/W2250759104","https://openalex.org/W2250863007","https://openalex.org/W2251457036","https://openalex.org/W2251572045","https://openalex.org/W2396779641","https://openalex.org/W2396881363","https://openalex.org/W2397636431","https://openalex.org/W2463981085","https://openalex.org/W2556166063","https://openalex.org/W2606308499","https://openalex.org/W2741908291","https://openalex.org/W2749701213","https://openalex.org/W2752867542","https://openalex.org/W2754117517","https://openalex.org/W2760845412","https://openalex.org/W2767899794","https://openalex.org/W2808838104","https://openalex.org/W2893928366","https://openalex.org/W2895296143","https://openalex.org/W2902405430","https://openalex.org/W2914361693","https://openalex.org/W2921264916","https://openalex.org/W2924728134","https://openalex.org/W2953902152","https://openalex.org/W2963386475","https://openalex.org/W2999282340","https://openalex.org/W3179072117","https://openalex.org/W4211116998","https://openalex.org/W4294536576","https://openalex.org/W6600725203","https://openalex.org/W6631166905","https://openalex.org/W6681875376","https://openalex.org/W6736731929"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W1590719878","https://openalex.org/W4244271513","https://openalex.org/W2100947578","https://openalex.org/W2161008081","https://openalex.org/W2365974527","https://openalex.org/W1555832326","https://openalex.org/W4306382224","https://openalex.org/W4298186509","https://openalex.org/W2556702969"],"abstract_inverted_index":{"In":[0],"the":[1,78,83],"medical":[2,18,56,93],"domain,":[3],"user-generated":[4],"social":[5,57],"media":[6],"text":[7],"is":[8],"increasingly":[9],"used":[10],"as":[11],"a":[12,45,50,92],"valuablecomplementary":[13],"knowledge":[14,24],"source":[15],"to":[16],"scientific":[17],"literature.":[19],"The":[20],"extraction":[21],"of":[22,35,73],"this":[23],"iscomplicated":[25],"by":[26],"colloquial":[27],"language":[28],"use":[29],"and":[30,66],"misspellings.":[31],"However,":[32],"lexical":[33,47],"normalization":[34],"suchdata":[36],"has":[37],"not":[38],"been":[39],"addressed":[40],"effectively.":[41],"This":[42],"paper":[43],"presents":[44],"data-driven":[46],"normalizationpipeline":[48],"with":[49,70],"novel":[51],"spelling":[52,63,87],"correction":[53,64,90],"module":[54],"for":[55,86],"media.":[58],"Our":[59],"method":[60],"significantlyoutperforms":[61],"state-of-the-art":[62],"methods":[65],"can":[67],"detect":[68],"mistakes":[69],"an":[71],"F1":[72],"0.63despite":[74],"extreme":[75],"imbalance":[76],"in":[77,91],"data.":[79],"We":[80],"also":[81],"present":[82],"first":[84],"corpus":[85],"mistake":[88],"detectionand":[89],"patient":[94],"forum.":[95]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
