{"id":"https://openalex.org/W4206668490","doi":"https://doi.org/10.1109/bigdata52589.2021.9672003","title":"Overcoming Rare-Language Discrimination in Multi-Lingual Sentiment Analysis","display_name":"Overcoming Rare-Language Discrimination in Multi-Lingual Sentiment Analysis","publication_year":2021,"publication_date":"2021-12-15","ids":{"openalex":"https://openalex.org/W4206668490","doi":"https://doi.org/10.1109/bigdata52589.2021.9672003"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata52589.2021.9672003","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9672003","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-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/A5032760851","display_name":"Jasmin Lampert","orcid":"https://orcid.org/0000-0002-0414-4525"},"institutions":[{"id":"https://openalex.org/I132118926","display_name":"Austrian Institute of Technology","ror":"https://ror.org/04knbh022","country_code":"AT","type":"facility","lineage":["https://openalex.org/I132118926"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Jasmin Lampert","raw_affiliation_strings":["Center for Digital Safety & Security, Competence Unit Data Science & Artificial Intelligence, AIT Austrian Institute of Technology, Vienna, Austria"],"affiliations":[{"raw_affiliation_string":"Center for Digital Safety & Security, Competence Unit Data Science & Artificial Intelligence, AIT Austrian Institute of Technology, Vienna, Austria","institution_ids":["https://openalex.org/I132118926"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068085751","display_name":"Christoph H. Lampert","orcid":"https://orcid.org/0000-0001-8622-7887"},"institutions":[{"id":"https://openalex.org/I157556583","display_name":"Institute of Science and Technology Austria","ror":"https://ror.org/03gnh5541","country_code":"AT","type":"education","lineage":["https://openalex.org/I157556583"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Christoph H. Lampert","raw_affiliation_strings":["Machine Learning and Computer Vision Group, Institute of Science and Technology Austria (IST Austria), Klosterneuburg, Austria"],"affiliations":[{"raw_affiliation_string":"Machine Learning and Computer Vision Group, Institute of Science and Technology Austria (IST Austria), Klosterneuburg, Austria","institution_ids":["https://openalex.org/I157556583"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5032760851"],"corresponding_institution_ids":["https://openalex.org/I132118926"],"apc_list":null,"apc_paid":null,"fwci":0.754,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.75257057,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5185","last_page":"5192"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":1.0,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":1.0,"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":0.9994999766349792,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9966999888420105,"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":0.8552139401435852},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"Sentiment analysis","score":0.6863695979118347},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5675937533378601},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.5473650693893433},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5338068604469299},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5210637450218201},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.519779622554779},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5139302611351013},{"id":"https://openalex.org/keywords/emoji","display_name":"Emoji","score":0.5101566910743713},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.4610402584075928},{"id":"https://openalex.org/keywords/proxy","display_name":"Proxy (statistics)","score":0.4226458966732025},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4176815152168274},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.26445627212524414},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1828315258026123}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8552139401435852},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.6863695979118347},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5675937533378601},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.5473650693893433},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5338068604469299},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5210637450218201},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.519779622554779},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5139302611351013},{"id":"https://openalex.org/C2779247141","wikidata":"https://www.wikidata.org/wiki/Q1049294","display_name":"Emoji","level":3,"score":0.5101566910743713},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.4610402584075928},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.4226458966732025},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4176815152168274},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.26445627212524414},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1828315258026123},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata52589.2021.9672003","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9672003","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W102786397","https://openalex.org/W654652841","https://openalex.org/W1522301498","https://openalex.org/W1581231885","https://openalex.org/W1614298861","https://openalex.org/W1996892032","https://openalex.org/W2076689724","https://openalex.org/W2099813784","https://openalex.org/W2397944984","https://openalex.org/W2531867140","https://openalex.org/W2538660910","https://openalex.org/W2575143348","https://openalex.org/W2607108970","https://openalex.org/W2611614234","https://openalex.org/W2741602058","https://openalex.org/W2770602608","https://openalex.org/W2792883466","https://openalex.org/W2803201508","https://openalex.org/W2891896107","https://openalex.org/W2990199592","https://openalex.org/W2999786665","https://openalex.org/W3037850663","https://openalex.org/W3094733139","https://openalex.org/W3100806282","https://openalex.org/W3166365810","https://openalex.org/W4287693250","https://openalex.org/W6631190155","https://openalex.org/W6636510571","https://openalex.org/W6781494728","https://openalex.org/W6785262283"],"related_works":["https://openalex.org/W2758548316","https://openalex.org/W3005503605","https://openalex.org/W151193258","https://openalex.org/W1607472309","https://openalex.org/W3107474891","https://openalex.org/W2898635241","https://openalex.org/W38394648","https://openalex.org/W1964135532","https://openalex.org/W3152966760","https://openalex.org/W2251948458"],"abstract_inverted_index":{"The":[0,163,201],"digitalization":[1],"of":[2,6,15,31,64,68,110,173],"almost":[3,100],"all":[4],"aspects":[5],"our":[7,69,185,205],"everyday":[8],"lives":[9],"has":[10],"led":[11],"to":[12,136,157,167,211],"unprecedented":[13],"amounts":[14],"data":[16,56,193],"being":[17],"freely":[18],"available":[19,94,102],"on":[20,237],"the":[21,65,81,111,155,159,171,196,216,238],"Internet.":[22],"In":[23],"particular":[24,229],"social":[25],"media":[26],"platforms":[27],"provide":[28],"rich":[29],"sources":[30],"user-generated":[32],"data,":[33],"though":[34],"typically":[35],"in":[36,46,53,118,122,228],"unstructured":[37],"form,":[38],"and":[39,58,227],"with":[40,180],"high":[41],"diversity,":[42],"such":[43,54,85],"as":[44,86,175,223],"written":[45],"many":[47,160],"different":[48],"languages.Automatically":[49],"identifying":[50],"meaningful":[51],"information":[52],"big":[55],"resources":[57],"extracting":[59],"it":[60],"efficiently":[61],"is":[62,76,166,209],"one":[63],"ongoing":[66],"challenges":[67],"time.":[70],"A":[71],"common":[72],"step":[73,165],"for":[74,83,96,103,178,220,224],"this":[75,97,130,138],"sentiment":[77,213],"analysis,":[78],"which":[79,145],"forms":[80],"foundation":[82],"tasks":[84],"opinion":[87],"mining":[88],"or":[89,153],"trend":[90],"prediction.":[91],"Unfortunately,":[92],"publicly":[93],"tools":[95],"task":[98],"are":[99,120],"exclusively":[101],"English-language":[104],"texts.":[105],"Consequently,":[106],"a":[107,125,134,141,176],"large":[108,190],"fraction":[109],"Internet":[112],"users,":[113],"who":[114],"do":[115],"not":[116],"communicate":[117],"English,":[119],"ignored":[121],"automatized":[123],"studies,":[124],"phenomenon":[126],"called":[127],"rare-language":[128],"discrimination.In":[129],"work":[131],"we":[132,187],"propose":[133],"technique":[135],"overcome":[137],"problem":[139],"by":[140],"truly":[142],"multi-lingual":[143,181,207],"model,":[144],"can":[146],"be":[147],"trained":[148],"automatically":[149],"without":[150],"linguistic":[151],"knowledge":[152],"even":[154],"ability":[156],"read":[158],"target":[161],"languages.":[162],"main":[164],"combine":[168],"self-annotation,":[169],"specifically":[170],"use":[172],"emoticons":[174],"proxy":[177],"labels,":[179],"sentence":[182],"representations.To":[183],"evaluate":[184],"method":[186],"curated":[188],"several":[189],"datasets":[191],"from":[192],"obtained":[194],"via":[195],"free":[197],"Twitter":[198],"streaming":[199],"API.":[200],"results":[202],"show":[203],"that":[204],"proposed":[206],"training":[208,235],"able":[210],"achieve":[212],"predictions":[214],"at":[215],"same":[217,239],"quality":[218],"level":[219],"rare":[221],"languages":[222],"frequent":[225],"ones,":[226],"clearly":[230],"better":[231],"than":[232],"what":[233],"mono-lingual":[234],"achieves":[236],"data.":[240],"<sup":[241],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[242],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[243]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}