{"id":"https://openalex.org/W2963603716","doi":"https://doi.org/10.1145/2983323.2983362","title":"Characterizing Diseases from Unstructured Text","display_name":"Characterizing Diseases from Unstructured Text","publication_year":2016,"publication_date":"2016-10-24","ids":{"openalex":"https://openalex.org/W2963603716","doi":"https://doi.org/10.1145/2983323.2983362","mag":"2963603716"},"language":"en","primary_location":{"id":"doi:10.1145/2983323.2983362","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2983323.2983362","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM International on Conference on Information and Knowledge Management","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/A5103858234","display_name":"Saurav Ghosh","orcid":null},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Saurav Ghosh","raw_affiliation_strings":["Virginia Tech, Arlington, VA, USA"],"affiliations":[{"raw_affiliation_string":"Virginia Tech, Arlington, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103154375","display_name":"Prithwish Chakraborty","orcid":"https://orcid.org/0000-0003-1407-7677"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prithwish Chakraborty","raw_affiliation_strings":["Virginia Tech, Arlington, VA, USA"],"affiliations":[{"raw_affiliation_string":"Virginia Tech, Arlington, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089835503","display_name":"Emily Cohn","orcid":"https://orcid.org/0000-0001-6415-519X"},"institutions":[{"id":"https://openalex.org/I1288882113","display_name":"Boston Children's Hospital","ror":"https://ror.org/00dvg7y05","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1288882113"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Emily Cohn","raw_affiliation_strings":["Boston Children's Hospital, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Boston Children's Hospital, Boston, MA, USA","institution_ids":["https://openalex.org/I1288882113"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087882430","display_name":"John S. Brownstein","orcid":"https://orcid.org/0000-0001-8568-5317"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John S. Brownstein","raw_affiliation_strings":["Harvard Medical School, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Harvard Medical School, Boston, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035052603","display_name":"Naren Ramakrishnan","orcid":"https://orcid.org/0000-0002-1821-9743"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Naren Ramakrishnan","raw_affiliation_strings":["Virginia Tech, Arlington, VA, USA"],"affiliations":[{"raw_affiliation_string":"Virginia Tech, Arlington, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103858234"],"corresponding_institution_ids":["https://openalex.org/I859038795"],"apc_list":null,"apc_paid":null,"fwci":1.8557,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.86211896,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1129","last_page":"1138"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11819","display_name":"Data-Driven Disease Surveillance","score":0.992900013923645,"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":0.992900013923645,"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":0.989300012588501,"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/T10028","display_name":"Topic Modeling","score":0.9836999773979187,"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/word2vec","display_name":"Word2vec","score":0.9288615584373474},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8182703256607056},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6902080178260803},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6871246099472046},{"id":"https://openalex.org/keywords/trace","display_name":"TRACE (psycholinguistics)","score":0.6862780451774597},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5883439183235168},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.5266366004943848},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4872649908065796},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.48223814368247986},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4800663888454437},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42265868186950684},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4117829203605652},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.397230327129364},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.20313268899917603}],"concepts":[{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.9288615584373474},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8182703256607056},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6902080178260803},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6871246099472046},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.6862780451774597},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5883439183235168},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.5266366004943848},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4872649908065796},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.48223814368247986},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4800663888454437},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42265868186950684},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4117829203605652},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.397230327129364},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.20313268899917603},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2983323.2983362","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2983323.2983362","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM International on Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306116","display_name":"U.S. Department of the Interior","ror":"https://ror.org/03v0pmy70"},{"id":"https://openalex.org/F4320314744","display_name":"IBM Center for the Business of Government","ror":null},{"id":"https://openalex.org/F4320333452","display_name":"Interior Business Center","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W100623710","https://openalex.org/W1615991656","https://openalex.org/W1662133657","https://openalex.org/W1999529874","https://openalex.org/W2006085716","https://openalex.org/W2117130368","https://openalex.org/W2120467164","https://openalex.org/W2125031621","https://openalex.org/W2128870637","https://openalex.org/W2131462252","https://openalex.org/W2141599568","https://openalex.org/W2158139315","https://openalex.org/W2158899491","https://openalex.org/W2250189634","https://openalex.org/W2250539671","https://openalex.org/W2251771443","https://openalex.org/W2251803266","https://openalex.org/W2403186103","https://openalex.org/W2407072560","https://openalex.org/W2597289420","https://openalex.org/W2950133940","https://openalex.org/W2950577311","https://openalex.org/W2997185401","https://openalex.org/W2997617958"],"related_works":["https://openalex.org/W2995505879","https://openalex.org/W4301121195","https://openalex.org/W2408387521","https://openalex.org/W3107535086","https://openalex.org/W2412133615","https://openalex.org/W3157315903","https://openalex.org/W4206379985","https://openalex.org/W2747424680","https://openalex.org/W3204309793","https://openalex.org/W4298857951"],"abstract_inverted_index":{"Traditional":[0],"disease":[1,48,76],"surveillance":[2,29],"can":[3],"be":[4],"augmented":[5],"with":[6],"a":[7,47],"wide":[8],"variety":[9],"of":[10,28,119],"real-time":[11],"sources":[12,21],"such":[13,31,121],"as,":[14],"news":[15,66],"and":[16,35,57,78,125],"social":[17],"media.":[18],"However,":[19],"these":[20,70],"are":[22],"in":[23,108],"general":[24],"unstructured":[25],"and,":[26],"construction":[27],"tools":[30],"as":[32,60,122],"taxonomical":[33,114],"correlations":[34],"trace":[36],"mapping":[37],"involves":[38],"considerable":[39],"human":[40,84],"supervision.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45],"motivate":[46],"vocabulary":[49],"driven":[50],"word2vec":[51,96],"model":[52,55,81,90],"(Dis2Vec)":[53],"to":[54,73,111],"diseases":[56,120],"constituent":[58],"attributes":[59,115],"word":[61,71],"embeddings":[62,72],"from":[63],"the":[64],"HealthMap":[65],"corpus.":[67],"We":[68,87],"use":[69],"automatically":[74],"create":[75],"taxonomies":[77],"evaluate":[79],"our":[80,89],"against":[82,92],"corresponding":[83],"annotated":[85],"taxonomies.":[86],"compare":[88],"accuracies":[91],"several":[93],"state-of-the":[94],"art":[95],"methods.":[97],"Our":[98],"results":[99],"demonstrate":[100],"that":[101],"Dis2Vec":[102],"outperforms":[103],"traditional":[104],"distributed":[105],"vector":[106],"representations":[107],"its":[109],"ability":[110],"faithfully":[112],"capture":[113],"across":[116],"different":[117],"class":[118],"endemic,":[123],"emerging":[124],"rare.":[126]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}