{"id":"https://openalex.org/W3132770720","doi":"https://doi.org/10.1038/s41598-021-83926-2","title":"Infectious disease outbreak prediction using media articles with machine learning models","display_name":"Infectious disease outbreak prediction using media articles with machine learning models","publication_year":2021,"publication_date":"2021-02-24","ids":{"openalex":"https://openalex.org/W3132770720","doi":"https://doi.org/10.1038/s41598-021-83926-2","mag":"3132770720","pmid":"https://pubmed.ncbi.nlm.nih.gov/33627706","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/7904826"},"language":"en","primary_location":{"id":"doi:10.1038/s41598-021-83926-2","doi":"https://doi.org/10.1038/s41598-021-83926-2","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41598-021-83926-2","pdf_url":"https://www.nature.com/articles/s41598-021-83926-2.pdf","source":{"id":"https://openalex.org/S196734849","display_name":"Scientific Reports","issn_l":"2045-2322","issn":["2045-2322"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Reports","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.nature.com/articles/s41598-021-83926-2.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101886886","display_name":"Juhyeon Kim","orcid":"https://orcid.org/0000-0001-6466-375X","observed_orcids":["https://orcid.org/0000-0001-6466-375X"]},"institutions":[{"id":"https://openalex.org/I4210151417","display_name":"Korea Research Institute of Chemical Technology","ror":"https://ror.org/043k4kk20","country_code":"KR","type":"facility","lineage":["https://openalex.org/I4210151417"]},{"id":"https://openalex.org/I878022262","display_name":"Korea Institute of Science & Technology Information","ror":"https://ror.org/01k4yrm29","country_code":"KR","type":"facility","lineage":["https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098","https://openalex.org/I878022262"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Juhyeon Kim","raw_affiliation_strings":["Center for Convergent Research of Emerging Virus Infection, Korea Research Institute of Chemical Technology, Yuseong-gu, Daejeon, Korea","Department of Data-Centric Problem Solving Research, Korea Institute of Science and Technology Information, Yuseong-gu, Daejeon, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Convergent Research of Emerging Virus Infection, Korea Research Institute of Chemical Technology, Yuseong-gu, Daejeon, Korea","institution_ids":["https://openalex.org/I4210151417"]},{"raw_affiliation_string":"Department of Data-Centric Problem Solving Research, Korea Institute of Science and Technology Information, Yuseong-gu, Daejeon, Korea","institution_ids":["https://openalex.org/I878022262"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034655436","display_name":"Insung Ahn","orcid":"https://orcid.org/0000-0003-1171-1206","observed_orcids":["https://orcid.org/0000-0003-1171-1206"]},"institutions":[{"id":"https://openalex.org/I4210151417","display_name":"Korea Research Institute of Chemical Technology","ror":"https://ror.org/043k4kk20","country_code":"KR","type":"facility","lineage":["https://openalex.org/I4210151417"]},{"id":"https://openalex.org/I878022262","display_name":"Korea Institute of Science & Technology Information","ror":"https://ror.org/01k4yrm29","country_code":"KR","type":"facility","lineage":["https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098","https://openalex.org/I878022262"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Insung Ahn","raw_affiliation_strings":["Center for Convergent Research of Emerging Virus Infection, Korea Research Institute of Chemical Technology, Yuseong-gu, Daejeon, Korea. isahn@kisti.re.kr","Department of Data-Centric Problem Solving Research, Korea Institute of Science and Technology Information, Yuseong-gu, Daejeon, Korea. isahn@kisti.re.kr","Department of Data-Centric Problem Solving Research, Korea Institute of Science and Technology Information, Yuseong-gu, Daejeon, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Convergent Research of Emerging Virus Infection, Korea Research Institute of Chemical Technology, Yuseong-gu, Daejeon, Korea. isahn@kisti.re.kr","institution_ids":["https://openalex.org/I4210151417"]},{"raw_affiliation_string":"Department of Data-Centric Problem Solving Research, Korea Institute of Science and Technology Information, Yuseong-gu, Daejeon, Korea. isahn@kisti.re.kr","institution_ids":["https://openalex.org/I878022262"]},{"raw_affiliation_string":"Department of Data-Centric Problem Solving Research, Korea Institute of Science and Technology Information, Yuseong-gu, Daejeon, Korea","institution_ids":["https://openalex.org/I878022262"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5034655436"],"corresponding_institution_ids":["https://openalex.org/I4210151417","https://openalex.org/I878022262"],"apc_list":{"value":1990,"currency":"USD","value_usd":1990},"apc_paid":{"value":1990,"currency":"USD","value_usd":1990},"fwci":7.2874,"has_fulltext":true,"cited_by_count":63,"citation_normalized_percentile":{"value":0.98333626,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":92,"max":100},"biblio":{"volume":"11","issue":"1","first_page":"4413","last_page":"4413"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9404000043869019,"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":0.9404000043869019,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.011900000274181366,"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":0.006300000008195639,"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/emerging-infectious-diseases","display_name":"emerging infectious diseases","score":0.996999979019165},{"id":"https://openalex.org/keywords/news-articles","display_name":"news articles","score":0.7400000095367432},{"id":"https://openalex.org/keywords/media-data","display_name":"media data","score":0.5789999961853027},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"support vector machine","score":0.7049999833106995},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"semi-supervised learning","score":0.9990000128746033},{"id":"https://openalex.org/keywords/deep-neural-network","display_name":"deep neural network","score":0.8960000276565552},{"id":"https://openalex.org/keywords/outbreak-detection","display_name":"outbreak detection","score":0.5009999871253967}],"concepts":[{"id":"https://openalex.org/C524204448","wikidata":"https://www.wikidata.org/wiki/Q788926","display_name":"Infectious disease (medical specialty)","level":3,"score":0.8385481238365173},{"id":"https://openalex.org/C116675565","wikidata":"https://www.wikidata.org/wiki/Q3241045","display_name":"Outbreak","level":2,"score":0.7661896347999573},{"id":"https://openalex.org/C2779134260","wikidata":"https://www.wikidata.org/wiki/Q12136","display_name":"Disease","level":2,"score":0.7421029806137085},{"id":"https://openalex.org/C2779973787","wikidata":"https://www.wikidata.org/wiki/Q609748","display_name":"Emerging infectious disease","level":3,"score":0.7130340337753296},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.5367075204849243},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4728413224220276},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.45589685440063477},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4293448030948639},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4145217537879944},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.3396376669406891},{"id":"https://openalex.org/C159047783","wikidata":"https://www.wikidata.org/wiki/Q7215","display_name":"Virology","level":1,"score":0.2459966242313385},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.19991061091423035},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.13203534483909607}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003141","descriptor_name":"Communicable Diseases","qualifier_ui":"Q000453","qualifier_name":"epidemiology","is_major_topic":true},{"descriptor_ui":"D004196","descriptor_name":"Disease Outbreaks","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008402","descriptor_name":"Mass Media","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":true},{"descriptor_ui":"D014943","descriptor_name":"Global Health","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D021821","descriptor_name":"Communicable Diseases, Emerging","qualifier_ui":"Q000453","qualifier_name":"epidemiology","is_major_topic":true},{"descriptor_ui":"D058872","descriptor_name":"Epidemics","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1038/s41598-021-83926-2","doi":"https://doi.org/10.1038/s41598-021-83926-2","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41598-021-83926-2","pdf_url":"https://www.nature.com/articles/s41598-021-83926-2.pdf","source":{"id":"https://openalex.org/S196734849","display_name":"Scientific Reports","issn_l":"2045-2322","issn":["2045-2322"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Reports","raw_type":"journal-article"},{"id":"pmid:33627706","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33627706","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific reports","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:7904826","doi":null,"is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC7904826/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sci Rep","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:497accacf95044c78f0128a73957f211","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/497accacf95044c78f0128a73957f211","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scientific Reports, Vol 11, Iss 1, Pp 1-13 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1038/s41598-021-83926-2","doi":"https://doi.org/10.1038/s41598-021-83926-2","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41598-021-83926-2","pdf_url":"https://www.nature.com/articles/s41598-021-83926-2.pdf","source":{"id":"https://openalex.org/S196734849","display_name":"Scientific Reports","issn_l":"2045-2322","issn":["2045-2322"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Reports","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","score":0.8048999905586243,"display_name":"Good health and well-being"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G2485918710","display_name":null,"funder_award_id":"CRC-16-01- KRICT","funder_id":"https://openalex.org/F4320325370","funder_display_name":"National Research Council of Science and Technology"},{"id":"https://openalex.org/G395415078","display_name":null,"funder_award_id":"2016M3A9B6915714","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G640993407","display_name":null,"funder_award_id":"CRC-16- 01-KRICT","funder_id":"https://openalex.org/F4320322030","funder_display_name":"Ministry of Science, ICT and Future Planning"},{"id":"https://openalex.org/G6792902424","display_name":null,"funder_award_id":"CRC-16-01-KRICT","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322030","display_name":"Ministry of Science, ICT and Future Planning","ror":"https://ror.org/032e49973"},{"id":"https://openalex.org/F4320322101","display_name":"Korea Research Institute of Chemical Technology","ror":"https://ror.org/043k4kk20"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320325370","display_name":"National Research Council of Science and Technology","ror":"https://ror.org/058rymf81"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3132770720.pdf","grobid_xml":"https://content.openalex.org/works/W3132770720.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1493256835","https://openalex.org/W1541774929","https://openalex.org/W1993926867","https://openalex.org/W1996608975","https://openalex.org/W2004826528","https://openalex.org/W2100776472","https://openalex.org/W2132346211","https://openalex.org/W2172269818","https://openalex.org/W2340224680","https://openalex.org/W2412774630","https://openalex.org/W2417168758","https://openalex.org/W2610260148","https://openalex.org/W2910124299","https://openalex.org/W2945054730","https://openalex.org/W2963703678","https://openalex.org/W2998574456"],"related_works":["https://openalex.org/W4388110323","https://openalex.org/W4318819061","https://openalex.org/W2945054730","https://openalex.org/W4286565516","https://openalex.org/W7217440490","https://openalex.org/W2598289997","https://openalex.org/W2520498909","https://openalex.org/W7128365536","https://openalex.org/W4403919239","https://openalex.org/W2883585595"],"abstract_inverted_index":{"When":[0],"a":[1,9,98,113],"newly":[2,31,182],"emerging":[3,48,61,183,227],"infectious":[4,45,62,73,87,100,149,161,167,184,228],"disease":[5,29,63,74,88,101,162,168],"breaks":[6],"out":[7],"in":[8,136,217],"country,":[10],"it":[11,79],"brings":[12],"critical":[13],"damage":[14],"to":[15,83,97,148,151,159,166,171,210,222],"both":[16],"human":[17,52],"health":[18,53],"conditions":[19],"and":[20,33,49,77,111,201,221],"the":[21,58,69,190,212,218,224],"national":[22],"economy.":[23],"For":[24,55,105],"this":[25,56,137,177],"reason,":[26,57],"apprehending":[27],"which":[28],"will":[30,89],"emerge,":[32],"preparing":[34],"countermeasures":[35],"for":[36,208],"that":[37,129,145],"disease,":[38,150],"are":[39,47],"required.":[40,120],"Many":[41],"different":[42],"types":[43],"of":[44,60,72,214,226],"diseases":[46,185],"threatening":[50],"global":[51],"conditions.":[54],"detection":[59],"pattern":[64,225],"is":[65,80,102,119],"critical.":[66],"However,":[67],"as":[68],"epidemic":[70],"spread":[71],"occurs":[75],"sporadically":[76],"rapidly,":[78],"not":[81,103],"easy":[82],"predict":[84,160],"whether":[85],"an":[86],"emerge":[90],"or":[91],"not.":[92],"Furthermore,":[93],"accumulating":[94],"data":[95,110,118,155],"related":[96,147,165],"specific":[99],"easy.":[104],"these":[106,117],"reasons,":[107],"finding":[108],"useful":[109],"building":[112],"prediction":[114,209],"model":[115],"with":[116],"The":[121],"Internet":[122,141],"press":[123],"releases":[124],"numerous":[125],"articles":[126,142],"every":[127],"day":[128],"rapidly":[130],"reflect":[131],"currently":[132],"pending":[133],"issues.":[134],"Thus,":[135],"research,":[138],"we":[139,179],"accumulated":[140],"from":[143,169],"Medisys":[144],"were":[146,174,206],"see":[152],"if":[153,181],"news":[154,191],"could":[156,186],"be":[157,187],"used":[158,207],"outbreak.":[163],"Articles":[164],"January":[170],"December":[172],"2019":[173],"collected.":[175],"In":[176],"study,":[178],"evaluated":[180],"detected":[188],"using":[189],"article":[192],"data.":[193],"Support":[194],"Vector":[195],"Machine":[196],"(SVM),":[197],"Semi-supervised":[198],"Learning":[199],"(SSL),":[200],"Deep":[202],"Neural":[203],"Network":[204],"(DNN)":[205],"examine":[211],"use":[213],"information":[215],"embedded":[216],"web":[219],"articles:":[220],"detect":[223],"disease.":[229]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":21},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":2}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2021-03-01T00:00:00"}
