{"id":"https://openalex.org/W4391097721","doi":"https://doi.org/10.1109/bigdata59044.2023.10386694","title":"UCE-FID: Using Large Unlabeled, Medium Crowdsourced-Labeled, and Small Expert-Labeled Tweets for Foodborne Illness Detection","display_name":"UCE-FID: Using Large Unlabeled, Medium Crowdsourced-Labeled, and Small Expert-Labeled Tweets for Foodborne Illness Detection","publication_year":2023,"publication_date":"2023-12-15","ids":{"openalex":"https://openalex.org/W4391097721","doi":"https://doi.org/10.1109/bigdata59044.2023.10386694"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata59044.2023.10386694","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata59044.2023.10386694","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5067370045","display_name":"Ruofan Hu","orcid":"https://orcid.org/0000-0003-4831-2671"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruofan Hu","raw_affiliation_strings":["Worcester Polytechnic Institute,Data Science Program,Worcester,USA","Data Science Program, Worcester Polytechnic Institute, Worcester, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute,Data Science Program,Worcester,USA","institution_ids":["https://openalex.org/I107077323"]},{"raw_affiliation_string":"Data Science Program, Worcester Polytechnic Institute, Worcester, USA","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100629138","display_name":"Dongyu Zhang","orcid":"https://orcid.org/0000-0003-2099-5837"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dongyu Zhang","raw_affiliation_strings":["Worcester Polytechnic Institute,Data Science Program,Worcester,USA","Data Science Program, Worcester Polytechnic Institute, Worcester, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute,Data Science Program,Worcester,USA","institution_ids":["https://openalex.org/I107077323"]},{"raw_affiliation_string":"Data Science Program, Worcester Polytechnic Institute, Worcester, USA","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039601741","display_name":"D. Tao","orcid":"https://orcid.org/0009-0000-8101-0099"},"institutions":[{"id":"https://openalex.org/I4210126646","display_name":"Vanke (China)","ror":"https://ror.org/0329dzd04","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210126646"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dandan Tao","raw_affiliation_strings":["Tsinghua University,Vanke School of Public Health,Beijing,China","Vanke School of Public Health, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Vanke School of Public Health,Beijing,China","institution_ids":["https://openalex.org/I4210126646","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Vanke School of Public Health, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I4210126646","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014608800","display_name":"Huayi Zhang","orcid":"https://orcid.org/0009-0004-7874-8542"},"institutions":[{"id":"https://openalex.org/I4210091247","display_name":"University for Peace","ror":"https://ror.org/00cxrw595","country_code":"CR","type":"education","lineage":["https://openalex.org/I1286959531","https://openalex.org/I4210091247"]}],"countries":["CR"],"is_corresponding":false,"raw_author_name":"Huayi Zhang","raw_affiliation_strings":["ByteDance,San Jose,USA","ByteDance, San Jose, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance,San Jose,USA","institution_ids":["https://openalex.org/I4210091247"]},{"raw_affiliation_string":"ByteDance, San Jose, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101876018","display_name":"Hao Feng","orcid":"https://orcid.org/0009-0008-4099-4886"},"institutions":[{"id":"https://openalex.org/I35777872","display_name":"North Carolina Agricultural and Technical State University","ror":"https://ror.org/02aze4h65","country_code":"US","type":"education","lineage":["https://openalex.org/I35777872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Feng","raw_affiliation_strings":["North Carolina A&T State University,College of Ag&Environ Sciences,Greensboro,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina A&T State University,College of Ag&Environ Sciences,Greensboro,USA","institution_ids":["https://openalex.org/I35777872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008269094","display_name":"Elke A. Rundensteiner","orcid":"https://orcid.org/0000-0001-5375-9254"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elke Rundensteiner","raw_affiliation_strings":["Worcester Polytechnic Institute,Computer Science/Data Science Program,Worcester,USA","Computer Science/Data Science Program, Worcester Polytechnic Institute, Worcester, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute,Computer Science/Data Science Program,Worcester,USA","institution_ids":["https://openalex.org/I107077323"]},{"raw_affiliation_string":"Computer Science/Data Science Program, Worcester Polytechnic Institute, Worcester, USA","institution_ids":["https://openalex.org/I107077323"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"63","issue":null,"first_page":"5250","last_page":"5259"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9832000136375427,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9832000136375427,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9750000238418579,"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/T11243","display_name":"Respiratory viral infections research","score":0.9664000272750854,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.7249060273170471},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6928374767303467},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5245664119720459},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49674302339553833},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.4815088212490082},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.47390687465667725},{"id":"https://openalex.org/keywords/scarcity","display_name":"Scarcity","score":0.4579628109931946},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4312891960144043},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4130192995071411},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.12042948603630066}],"concepts":[{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.7249060273170471},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6928374767303467},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5245664119720459},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49674302339553833},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.4815088212490082},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.47390687465667725},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.4579628109931946},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4312891960144043},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4130192995071411},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.12042948603630066},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/bigdata59044.2023.10386694","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata59044.2023.10386694","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/2","display_name":"Zero hunger"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320317074","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1486638903","https://openalex.org/W1522301498","https://openalex.org/W2021157254","https://openalex.org/W2330491661","https://openalex.org/W2564011418","https://openalex.org/W2598946096","https://openalex.org/W2783923625","https://openalex.org/W2807122929","https://openalex.org/W2886705558","https://openalex.org/W2891244534","https://openalex.org/W2896457183","https://openalex.org/W2905974357","https://openalex.org/W2947380870","https://openalex.org/W2962369866","https://openalex.org/W2965373594","https://openalex.org/W2979814622","https://openalex.org/W2981952041","https://openalex.org/W2996108195","https://openalex.org/W3037798832","https://openalex.org/W3042609801","https://openalex.org/W3042611018","https://openalex.org/W3122023070","https://openalex.org/W3166159471","https://openalex.org/W3167251133","https://openalex.org/W3169311455","https://openalex.org/W3172399575","https://openalex.org/W3180562345","https://openalex.org/W3196927126","https://openalex.org/W3198843179","https://openalex.org/W3205500251","https://openalex.org/W3205830981","https://openalex.org/W4212774754","https://openalex.org/W4226211505","https://openalex.org/W4312256146","https://openalex.org/W4312373370","https://openalex.org/W4318348348","https://openalex.org/W4377088196","https://openalex.org/W4385068704","https://openalex.org/W4387776622","https://openalex.org/W6600005792","https://openalex.org/W6631190155","https://openalex.org/W6714414233","https://openalex.org/W6750523955","https://openalex.org/W6755207826","https://openalex.org/W6763430915","https://openalex.org/W6765939562","https://openalex.org/W6766673545","https://openalex.org/W6771630921","https://openalex.org/W6773005947","https://openalex.org/W6774314701","https://openalex.org/W6780353226","https://openalex.org/W6802704751","https://openalex.org/W6802864417","https://openalex.org/W6838113493","https://openalex.org/W6849385481"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W1571141552","https://openalex.org/W4391636338","https://openalex.org/W4386067343","https://openalex.org/W4294250823","https://openalex.org/W2093086151","https://openalex.org/W55936454","https://openalex.org/W2095572632","https://openalex.org/W2944249426","https://openalex.org/W4294609170"],"abstract_inverted_index":{"Foodborne":[0],"illnesses":[1],"significantly":[2],"impact":[3],"public":[4],"health.":[5],"Deep":[6],"learning":[7,97],"surveillance":[8,233],"applications":[9],"using":[10],"social":[11,66],"media":[12,67],"data":[13,159],"aim":[14],"to":[15,35,128,134,138,148,191,219,229],"detect":[16],"early":[17],"warning":[18],"signals.":[19],"However,":[20],"labeling":[21],"foodborne":[22,58,100,230],"illness-related":[23,59],"tweets":[24,44,60,107,118,137,144,202],"for":[25,43,99,222],"model":[26,199],"training":[27],"requires":[28],"extensive":[29],"human":[30],"resources,":[31],"making":[32,84],"it":[33],"challenging":[34],"collect":[36],"a":[37,46,75,95,123,130,183],"sufficient":[38],"number":[39],"of":[40,57,65,132,186,213,225],"high-quality":[41],"labels":[42],"within":[45],"limited":[47],"budget.":[48],"The":[49],"severe":[50],"class":[51,152,176],"imbalance":[52,177],"resulting":[53],"from":[54],"the":[55,62,70,81,150,197,210,217],"scarcity":[56],"among":[61],"vast":[63],"volume":[64],"further":[68],"exacerbates":[69],"problem.":[71],"Classifiers":[72],"trained":[73,198],"on":[74,156,182],"classimbalanced":[76],"dataset":[77],"are":[78],"biased":[79],"towards":[80],"majority":[82],"class,":[83],"accurate":[85],"detection":[86,102],"difficult.":[87],"To":[88],"overcome":[89],"these":[90],"challenges,":[91],"we":[92],"propose":[93],"EGAL,":[94,207],"deep":[96],"framework":[98],"illness":[101,231],"that":[103,161],"uses":[104],"small":[105],"expert-labeled":[106,172],"augmented":[108],"by":[109,116,120,209],"crowdsourced-labeled":[110],"and":[111,175],"massive":[112],"unlabeled":[113],"data.":[114],"Specifically,":[115],"leveraging":[117],"labeled":[119,136],"experts":[121],"as":[122],"reward":[124],"set,":[125],"EGAL":[126,162],"learns":[127],"assign":[129],"weight":[131],"zero":[133],"incorrectly":[135],"mitigate":[139],"their":[140],"negative":[141],"influence.":[142],"Other":[143],"receive":[145],"proportionate":[146],"weights":[147],"counter-balance":[149],"unbalanced":[151],"distribution.":[153],"Extensive":[154],"experiments":[155],"real-world":[157],"TWEET-FID":[158],"show":[160],"outperforms":[163],"strong":[164],"baseline":[165],"models":[166],"across":[167],"different":[168],"settings,":[169],"including":[170],"varying":[171],"set":[173],"sizes":[174],"ratios.":[178],"A":[179],"case":[180],"study":[181],"multistate":[184],"outbreak":[185,205,232],"Salmonella":[187],"Typhimurium":[188],"infection":[189],"linked":[190],"packaged":[192],"salad":[193],"greens":[194],"demonstrates":[195],"how":[196],"captures":[200],"relevant":[201],"offering":[203],"valuable":[204],"insights.":[206],"funded":[208],"U.S.":[211],"Department":[212],"Agriculture":[214],"(USDA),":[215],"has":[216],"potential":[218],"be":[220],"deployed":[221],"real-time":[223],"analysis":[224],"tweet":[226],"streaming,":[227],"contributing":[228],"efforts.":[234]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}