{"id":"https://openalex.org/W2783923625","doi":"https://doi.org/10.1093/jamia/ocx093","title":"Discovering foodborne illness in online restaurant reviews","display_name":"Discovering foodborne illness in online restaurant reviews","publication_year":2017,"publication_date":"2017-09-25","ids":{"openalex":"https://openalex.org/W2783923625","doi":"https://doi.org/10.1093/jamia/ocx093","mag":"2783923625","pmid":"https://pubmed.ncbi.nlm.nih.gov/29329402","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/7647154"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1093/jamia/ocx093","pdf_url":"https://academic.oup.com/jamia/article-pdf/25/12/1586/27090541/ocx093.pdf","source":{"id":"https://openalex.org/S129839026","display_name":"Journal of the American Medical Informatics Association","issn_l":"1067-5027","issn":["1067-5027","1527-974X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311647","https://openalex.org/P4310311648"],"host_organization_lineage_names":["University of Oxford","Oxford University Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/jamia/article-pdf/25/12/1586/27090541/ocx093.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087973101","display_name":"Thomas Effland","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Thomas Effland","raw_affiliation_strings":["Computer Science Department, Data Science Institute, Columbia University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Data Science Institute, Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047842469","display_name":"Anna Lawson","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anna Lawson","raw_affiliation_strings":["Computer Science Department, Data Science Institute, Columbia University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Data Science Institute, Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033815849","display_name":"Sharon Balter","orcid":null},"institutions":[{"id":"https://openalex.org/I1334095494","display_name":"New York City Department of Health and Mental Hygiene","ror":"https://ror.org/01gst4g14","country_code":"US","type":"government","lineage":["https://openalex.org/I1334095494"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sharon Balter","raw_affiliation_strings":["Bureau of Communicable Disease, New York City Department of Health and Mental Hygiene, Queens, NY, USA"],"affiliations":[{"raw_affiliation_string":"Bureau of Communicable Disease, New York City Department of Health and Mental Hygiene, Queens, NY, USA","institution_ids":["https://openalex.org/I1334095494"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084310748","display_name":"Katelynn Devinney","orcid":"https://orcid.org/0000-0003-3395-1534"},"institutions":[{"id":"https://openalex.org/I1334095494","display_name":"New York City Department of Health and Mental Hygiene","ror":"https://ror.org/01gst4g14","country_code":"US","type":"government","lineage":["https://openalex.org/I1334095494"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katelynn Devinney","raw_affiliation_strings":["Bureau of Communicable Disease, New York City Department of Health and Mental Hygiene, Queens, NY, USA"],"affiliations":[{"raw_affiliation_string":"Bureau of Communicable Disease, New York City Department of Health and Mental Hygiene, Queens, NY, USA","institution_ids":["https://openalex.org/I1334095494"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110325246","display_name":"Vasudha Reddy","orcid":null},"institutions":[{"id":"https://openalex.org/I1334095494","display_name":"New York City Department of Health and Mental Hygiene","ror":"https://ror.org/01gst4g14","country_code":"US","type":"government","lineage":["https://openalex.org/I1334095494"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vasudha Reddy","raw_affiliation_strings":["Bureau of Communicable Disease, New York City Department of Health and Mental Hygiene, Queens, NY, USA"],"affiliations":[{"raw_affiliation_string":"Bureau of Communicable Disease, New York City Department of Health and Mental Hygiene, Queens, NY, USA","institution_ids":["https://openalex.org/I1334095494"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084549754","display_name":"HaeNa Waechter","orcid":"https://orcid.org/0000-0002-9507-2300"},"institutions":[{"id":"https://openalex.org/I1334095494","display_name":"New York City Department of Health and Mental Hygiene","ror":"https://ror.org/01gst4g14","country_code":"US","type":"government","lineage":["https://openalex.org/I1334095494"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"HaeNa Waechter","raw_affiliation_strings":["Bureau of Communicable Disease, New York City Department of Health and Mental Hygiene, Queens, NY, USA"],"affiliations":[{"raw_affiliation_string":"Bureau of Communicable Disease, New York City Department of Health and Mental Hygiene, Queens, NY, USA","institution_ids":["https://openalex.org/I1334095494"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080063580","display_name":"Luis Gravano","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luis Gravano","raw_affiliation_strings":["Computer Science Department, Data Science Institute, Columbia University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Data Science Institute, Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061246300","display_name":"Daniel Hsu","orcid":"https://orcid.org/0000-0002-3495-7113"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Hsu","raw_affiliation_strings":["Computer Science Department, Data Science Institute, Columbia University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Data Science Institute, Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5087973101"],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":{"value":3967,"currency":"USD","value_usd":3967,"provenance":"doaj"},"apc_paid":null,"fwci":3.897,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":50,"citation_normalized_percentile":{"value":0.917164,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"25","issue":"12","first_page":"1586","last_page":"1592"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9978,"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":0.9978,"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/T11957","display_name":"Food Safety and Hygiene","score":0.9775,"subfield":{"id":"https://openalex.org/subfields/1106","display_name":"Food Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12486","display_name":"Food Supply Chain Traceability","score":0.9159,"subfield":{"id":"https://openalex.org/subfields/1106","display_name":"Food Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/identification","display_name":"Identification","score":0.41294718}],"concepts":[{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6234487},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.60436994},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.56908715},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.56670433},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.54148084},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5298376},{"id":"https://openalex.org/C2776674806","wikidata":"https://www.wikidata.org/wiki/Q12135","display_name":"Mental illness","level":3,"score":0.46893597},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.41294718},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.27938014},{"id":"https://openalex.org/C134362201","wikidata":"https://www.wikidata.org/wiki/Q317309","display_name":"Mental health","level":2,"score":0.19025755},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.14196008},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"","qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004196","descriptor_name":"Disease Outbreaks","qualifier_ui":"","qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005517","descriptor_name":"Foodborne Diseases","qualifier_ui":"Q000175","qualifier_name":"diagnosis","is_major_topic":true},{"descriptor_ui":"D011159","descriptor_name":"Population Surveillance","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D012147","descriptor_name":"Restaurants","qualifier_ui":"","qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004196","descriptor_name":"Disease Outbreaks","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D005517","descriptor_name":"Foodborne Diseases","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D005517","descriptor_name":"Foodborne Diseases","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005517","descriptor_name":"Foodborne Diseases","qualifier_ui":"Q000453","qualifier_name":"epidemiology","is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016015","descriptor_name":"Logistic Models","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009519","descriptor_name":"New York City","qualifier_ui":"Q000453","qualifier_name":"epidemiology","is_major_topic":false},{"descriptor_ui":"D009519","descriptor_name":"New York City","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011159","descriptor_name":"Population Surveillance","qualifier_ui":"","qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1093/jamia/ocx093","pdf_url":"https://academic.oup.com/jamia/article-pdf/25/12/1586/27090541/ocx093.pdf","source":{"id":"https://openalex.org/S129839026","display_name":"Journal of the American Medical Informatics Association","issn_l":"1067-5027","issn":["1067-5027","1527-974X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311647","https://openalex.org/P4310311648"],"host_organization_lineage_names":["University of Oxford","Oxford University Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7647154","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,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29329402","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,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1093/jamia/ocx093","pdf_url":"https://academic.oup.com/jamia/article-pdf/25/12/1586/27090541/ocx093.pdf","source":{"id":"https://openalex.org/S129839026","display_name":"Journal of the American Medical Informatics Association","issn_l":"1067-5027","issn":["1067-5027","1527-974X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311647","https://openalex.org/P4310311648"],"host_organization_lineage_names":["University of Oxford","Oxford University Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being","score":0.62}],"grants":[{"funder":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation","award_id":"IIS-15-63785"},{"funder":"https://openalex.org/F4320306151","funder_display_name":"Alfred P. Sloan Foundation","award_id":"G-2015-14017"},{"funder":"https://openalex.org/F4320332162","funder_display_name":"Centers for Disease Control and Prevention","award_id":"NU90TP000546"}],"datasets":[],"versions":[],"referenced_works_count":22,"referenced_works":["https://openalex.org/W1736726159","https://openalex.org/W1995945562","https://openalex.org/W2043192041","https://openalex.org/W2075782082","https://openalex.org/W208461","https://openalex.org/W2119821739","https://openalex.org/W2120467164","https://openalex.org/W2125055259","https://openalex.org/W2148330046","https://openalex.org/W2151031807","https://openalex.org/W2160641460","https://openalex.org/W2161463970","https://openalex.org/W2167414951","https://openalex.org/W2409447780","https://openalex.org/W2564011418","https://openalex.org/W2612479270","https://openalex.org/W2797563284","https://openalex.org/W2903950532","https://openalex.org/W2911964244","https://openalex.org/W3149659392","https://openalex.org/W4239510810","https://openalex.org/W4300601563"],"related_works":["https://openalex.org/W96612179","https://openalex.org/W632915154","https://openalex.org/W4256492088","https://openalex.org/W4229499248","https://openalex.org/W3022067003","https://openalex.org/W2987774938","https://openalex.org/W2770234245","https://openalex.org/W2566006169","https://openalex.org/W2055733372","https://openalex.org/W1567818861"],"abstract_inverted_index":{"Abstract":[0],"Objective":[1],"We":[2,47,76,107,141],"developed":[3,78],"a":[4,56,59,68,79,88,113,119,197],"system":[5,22,95,199,209],"for":[6,40,50,84,153,163,182,240,254],"the":[7,26,136,175,186,214],"discovery":[8],"of":[9,31,94,115,135,159,177,216,222],"foodborne":[10,41,62,74,223,255],"illness":[11,42,63,224,256],"mentioned":[12],"in":[13,82,118,213],"online":[14],"Yelp":[15,39,253],"restaurant":[16],"reviews":[17,102,117],"using":[18,87],"text":[19],"classification.":[20],"The":[21],"is":[23],"used":[24,108],"by":[25,104,201],"New":[27,227],"York":[28,228],"City":[29,229],"Department":[30],"Health":[32],"and":[33,45,64,112,161,166,219],"Mental":[34],"Hygiene":[35],"(DOHMH)":[36],"to":[37,124,180,195,249],"monitor":[38,252],"complaints.":[43],"Materials":[44],"Methods":[46],"built":[48],"classifiers":[49,239],"2":[51],"tasks:":[52],"(1)":[53],"determining":[54,66],"if":[55,67],"review":[57,69],"indicated":[58,70],"person":[60],"experiencing":[61,73],"(2)":[65],"multiple":[71],"people":[72],"illness.":[75],"first":[77],"prototype":[80],"classifier":[81],"2012":[83],"both":[85,154,241],"tasks":[86,164],"small":[89],"labeled":[90,99,205],"dataset.":[91],"Over":[92],"years":[93],"deployment,":[96],"DOHMH":[97,247],"epidemiologists":[98,248],"13":[100],"526":[101],"selected":[103],"this":[105],"classifier.":[106],"these":[109],"biased":[110,204],"data":[111,150],"sample":[114],"complementary":[116],"principled":[120],"bias-adjusted":[121,148,190],"training":[122,191],"scheme":[123,192],"develop":[125],"significantly":[126],"improved":[127],"classifiers.":[128,139],"Finally,":[129],"we":[130],"performed":[131,151],"an":[132],"error":[133,171],"analysis":[134,172],"best":[137,152],"resulting":[138],"Results":[140],"found":[142],"that":[143,174],"logistic":[144],"regression":[145],"trained":[146],"with":[147,157,226],"augmented":[149],"classification":[155,198],"tasks,":[156,242],"F1-scores":[158],"87%":[160],"66%":[162],"1":[165],"2,":[167],"respectively.":[168],"Discussion":[169],"Our":[170,189,208,234],"revealed":[173],"inability":[176],"our":[178],"models":[179],"account":[181],"long":[183],"phrases":[184],"caused":[185],"most":[187],"errors.":[188],"illustrates":[193],"how":[194],"improve":[196],"iteratively":[200],"exploiting":[202],"available":[203],"data.":[206],"Conclusions":[207],"has":[210,236],"been":[211],"instrumental":[212],"identification":[215],"10":[217],"outbreaks":[218],"8523":[220],"complaints":[221],"associated":[225],"restaurants":[230],"since":[231],"July":[232],"2012.":[233],"evaluation":[235],"identified":[237],"strong":[238],"whose":[243],"deployment":[244],"will":[245],"allow":[246],"more":[250],"effectively":[251],"investigations.":[257]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2783923625","counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":1}],"updated_date":"2025-01-16T13:17:11.973191","created_date":"2018-01-26"}