{"id":"https://openalex.org/W2252027930","doi":"https://doi.org/10.18653/v1/w15-4302","title":"Challenges of studying and processing dialects in social media","display_name":"Challenges of studying and processing dialects in social media","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2252027930","doi":"https://doi.org/10.18653/v1/w15-4302","mag":"2252027930"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w15-4302","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-4302","pdf_url":"https://www.aclweb.org/anthology/W15-4302.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 Workshop on Noisy User-generated Text","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W15-4302.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049407823","display_name":"Anna J\u00f8rgensen","orcid":"https://orcid.org/0000-0001-5614-567X"},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Anna J\u00f8rgensen","raw_affiliation_strings":["University of Copenhagen Njalsgade 140 DK-2300 Copenhagen S"],"affiliations":[{"raw_affiliation_string":"University of Copenhagen Njalsgade 140 DK-2300 Copenhagen S","institution_ids":["https://openalex.org/I124055696"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084505122","display_name":"Dirk Hovy","orcid":"https://orcid.org/0000-0002-4618-3127"},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Dirk Hovy","raw_affiliation_strings":["University of Copenhagen Njalsgade 140 DK-2300 Copenhagen S"],"affiliations":[{"raw_affiliation_string":"University of Copenhagen Njalsgade 140 DK-2300 Copenhagen S","institution_ids":["https://openalex.org/I124055696"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018138946","display_name":"Anders S\u00f8gaard","orcid":"https://orcid.org/0000-0001-5250-4276"},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Anders S\u00f8gaard","raw_affiliation_strings":["University of Copenhagen Njalsgade 140 DK-2300 Copenhagen S"],"affiliations":[{"raw_affiliation_string":"University of Copenhagen Njalsgade 140 DK-2300 Copenhagen S","institution_ids":["https://openalex.org/I124055696"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5018138946"],"corresponding_institution_ids":["https://openalex.org/I124055696"],"apc_list":null,"apc_paid":null,"fwci":32.3948,"has_fulltext":true,"cited_by_count":61,"citation_normalized_percentile":{"value":0.99519706,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"9","last_page":"18"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11640","display_name":"Linguistic Variation and Morphology","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11640","display_name":"Linguistic Variation and Morphology","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9955999851226807,"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":0.9909999966621399,"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":0.7481704950332642},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7464948296546936},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.723554253578186},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6580169200897217},{"id":"https://openalex.org/keywords/vernacular","display_name":"Vernacular","score":0.6011239290237427},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5898197293281555},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.5465050935745239},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5344620943069458},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4709537923336029},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.18872064352035522}],"concepts":[{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.7481704950332642},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7464948296546936},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.723554253578186},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6580169200897217},{"id":"https://openalex.org/C2780386941","wikidata":"https://www.wikidata.org/wiki/Q1036511","display_name":"Vernacular","level":2,"score":0.6011239290237427},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5898197293281555},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.5465050935745239},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5344620943069458},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4709537923336029},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.18872064352035522},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/w15-4302","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-4302","pdf_url":"https://www.aclweb.org/anthology/W15-4302.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 Workshop on Noisy User-generated Text","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/8bc5d462-9e8f-4227-a953-0650fa32d310","is_oa":true,"landing_page_url":"http://www.aclweb.org/anthology/W15-4302","pdf_url":"https://aclanthology.org/W15-4302.pdf","source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"van Zee , A K , Hovy , D & S\u00f8gaard , A 2015 , Challenges of Studying and Processing Dialects in Social Media . in ACL 2015 Workshop on Noisy User-generated Text . Association for Computational Linguistics , Red Hoop, NY , pp. 9-18 . < http://www.aclweb.org/anthology/W15-4302 >","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.atira.dk:publications/8bc5d462-9e8f-4227-a953-0650fa32d310","is_oa":true,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/8bc5d462-9e8f-4227-a953-0650fa32d310","pdf_url":null,"source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"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":"van Zee , A K , Hovy , D & S\u00f8gaard , A 2015 , Challenges of Studying and Processing Dialects in Social Media . in ACL 2015 Workshop on Noisy User-generated Text . Association for Computational Linguistics , Red Hoop, NY , pp. 9-18 . < http://www.aclweb.org/anthology/W15-4302 >","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"doi:10.18653/v1/w15-4302","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-4302","pdf_url":"https://www.aclweb.org/anthology/W15-4302.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 Workshop on Noisy User-generated Text","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8700000047683716,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2252027930.pdf","grobid_xml":"https://content.openalex.org/works/W2252027930.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W400491622","https://openalex.org/W2002169143","https://openalex.org/W2017729405","https://openalex.org/W2019827344","https://openalex.org/W2032420854","https://openalex.org/W2077233185","https://openalex.org/W2082814186","https://openalex.org/W2100849402","https://openalex.org/W2115694763","https://openalex.org/W2142099338","https://openalex.org/W2143995218","https://openalex.org/W2144364794","https://openalex.org/W2164496512","https://openalex.org/W2171258802","https://openalex.org/W2250559305","https://openalex.org/W2251157848","https://openalex.org/W2251263615","https://openalex.org/W2251409655","https://openalex.org/W2252209719","https://openalex.org/W2293267779","https://openalex.org/W2488300226","https://openalex.org/W2586516948","https://openalex.org/W2605507719","https://openalex.org/W2949259776","https://openalex.org/W3098567718","https://openalex.org/W4252064922"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2100947578","https://openalex.org/W2161008081","https://openalex.org/W1555832326","https://openalex.org/W4298186509","https://openalex.org/W2556702969","https://openalex.org/W217221262","https://openalex.org/W611030372","https://openalex.org/W1974418053","https://openalex.org/W2081317458"],"abstract_inverted_index":{"Dialect":[0],"features":[1],"typically":[2],"do":[3],"not":[4],"make":[5],"it":[6],"into":[7],"formal":[8],"writing,":[9],"but":[10],"flourish":[11],"in":[12],"social":[13],"media.":[14],"This":[15],"enables":[16],"largescale":[17],"variational":[18],"studies.":[19]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
