{"id":"https://openalex.org/W2517596842","doi":"https://doi.org/10.18653/v1/w16-2917","title":"Construction of a Personal Experience Tweet Corpus for Health Surveillance","display_name":"Construction of a Personal Experience Tweet Corpus for Health Surveillance","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2517596842","doi":"https://doi.org/10.18653/v1/w16-2917","mag":"2517596842"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w16-2917","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-2917","pdf_url":"https://www.aclweb.org/anthology/W16-2917.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 15th Workshop on Biomedical Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W16-2917.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045470122","display_name":"Keyuan Jiang","orcid":"https://orcid.org/0000-0002-1565-3202"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Keyuan Jiang","raw_affiliation_strings":["Department of Computer Information Technology & Graphics Purdue University Northwest"],"affiliations":[{"raw_affiliation_string":"Department of Computer Information Technology & Graphics Purdue University Northwest","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041560944","display_name":"Ricardo A. Calix","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ricardo Calix","raw_affiliation_strings":["Department of Computer Information Technology & Graphics Purdue University Northwest"],"affiliations":[{"raw_affiliation_string":"Department of Computer Information Technology & Graphics Purdue University Northwest","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081918079","display_name":"Matrika Gupta","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matrika Gupta","raw_affiliation_strings":["Department of Computer Information Technology & Graphics Purdue University Northwest"],"affiliations":[{"raw_affiliation_string":"Department of Computer Information Technology & Graphics Purdue University Northwest","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5045470122"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.7115,"has_fulltext":true,"cited_by_count":27,"citation_normalized_percentile":{"value":0.93377562,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"128","last_page":"135"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9972000122070312,"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":0.9972000122070312,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9634000062942505,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9391000270843506,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.5641500949859619},{"id":"https://openalex.org/keywords/internet-privacy","display_name":"Internet privacy","score":0.43706029653549194},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3473100960254669},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.33129826188087463}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5641500949859619},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.43706029653549194},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3473100960254669},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.33129826188087463}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w16-2917","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-2917","pdf_url":"https://www.aclweb.org/anthology/W16-2917.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 15th Workshop on Biomedical Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w16-2917","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-2917","pdf_url":"https://www.aclweb.org/anthology/W16-2917.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 15th Workshop on Biomedical Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.6100000143051147}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2517596842.pdf","grobid_xml":"https://content.openalex.org/works/W2517596842.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W177032395","https://openalex.org/W1512104599","https://openalex.org/W1632327998","https://openalex.org/W1766594731","https://openalex.org/W1821634034","https://openalex.org/W1969894105","https://openalex.org/W1975587682","https://openalex.org/W2003834798","https://openalex.org/W2007628554","https://openalex.org/W2011273513","https://openalex.org/W2022783018","https://openalex.org/W2030864883","https://openalex.org/W2033640210","https://openalex.org/W2050735546","https://openalex.org/W2051964273","https://openalex.org/W2060916927","https://openalex.org/W2101196063","https://openalex.org/W2102742655","https://openalex.org/W2116265632","https://openalex.org/W2120390634","https://openalex.org/W2133990480","https://openalex.org/W2135035282","https://openalex.org/W2147194983","https://openalex.org/W2148325172","https://openalex.org/W2151919021","https://openalex.org/W2162336932","https://openalex.org/W2165530491","https://openalex.org/W2166701401","https://openalex.org/W2408368016","https://openalex.org/W2409447780","https://openalex.org/W3098522139"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2087861504","https://openalex.org/W2351790455","https://openalex.org/W2570974996","https://openalex.org/W2752793062","https://openalex.org/W1585501219","https://openalex.org/W1507112395","https://openalex.org/W2470158912","https://openalex.org/W1977921572","https://openalex.org/W2083439922"],"abstract_inverted_index":{"Studies":[0],"have":[1],"shown":[2],"that":[3,154,166],"Twitter":[4,27,173],"can":[5,75,157],"be":[6,158],"used":[7,145],"for":[8,22],"health":[9,23,163],"surveillance,":[10],"and":[11,34,125],"personal":[12],"experience":[13],"tweets":[14,118,123],"(PETs)":[15],"are":[16],"an":[17],"important":[18],"source":[19],"of":[20,49,58,64,80,88,95,116,128,142,171],"information":[21],"surveillance.":[24],"To":[25,91],"mine":[26],"data":[28,51],"requires":[29],"a":[30,41,55,70,85,98,114],"relatively":[31],"balanced":[32],"corpus":[33,42,100,115],"it":[35],"is":[36,152],"challenging":[37],"to":[38,44,102,136,160],"construct":[39],"such":[40],"due":[43],"the":[45,62,65,78,93,126],"labor-intensive":[46],"annotation":[47,89],"tasks":[48],"large":[50],"sets.":[52],"We":[53],"developed":[54],"bootstrap":[56],"method":[57],"finding":[59],"PETs":[60],"with":[61,84],"use":[63,167],"machine":[66,168],"learning-based":[67,169],"filter.":[68],"Through":[69],"few":[71],"iterations,":[72,113],"our":[73,96,155],"approach":[74,156],"efficiently":[76],"improve":[77],"balance":[79],"two":[81,129,140],"class":[82],"dataset":[83],"reduced":[86,133],"amount":[87],"work.":[90],"demonstrate":[92],"usefulness":[94],"method,":[97],"PET":[99],"related":[101],"effects":[103],"caused":[104],"by":[105],"4":[106],"dietary":[107],"supplements":[108],"was":[109,119,131],"constructed.":[110],"In":[111,138],"3":[112],"8,770":[117],"obtained":[120],"from":[121,134],"108,528":[122],"collected,":[124],"imbalance":[127],"classes":[130],"significantly":[132],"1:31":[135],"1:3.":[137],"addition,":[139],"out":[141],"three":[143],"classifiers":[144],"showed":[146],"improved":[147],"performance":[148],"over":[149],"iterations.":[150],"It":[151],"conceivable":[153],"applied":[159],"various":[161],"other":[162],"surveillance":[164],"studies":[165],"classifications":[170],"imbalanced":[172],"data.":[174]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}