{"id":"https://openalex.org/W2292460057","doi":null,"title":"Designing Domain Specific Word Embeddings: Applications to Disease Surveillance.","display_name":"Designing Domain Specific Word Embeddings: Applications to Disease Surveillance.","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2292460057","mag":"2292460057"},"language":"en","primary_location":{"id":"mag:2292460057","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1603.00106v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1603.00106v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103858234","display_name":"Saurav Ghosh","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saurav Ghosh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103154375","display_name":"Prithwish Chakraborty","orcid":"https://orcid.org/0000-0003-1407-7677","observed_orcids":["https://orcid.org/0000-0003-1407-7677"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prithwish Chakraborty","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-1407-7677","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089835503","display_name":"Emily L. Cohn","orcid":"https://orcid.org/0000-0001-6415-519X","observed_orcids":["https://orcid.org/0000-0001-6415-519X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emily Cohn","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087882430","display_name":"John S. Brownstein","orcid":"https://orcid.org/0000-0001-8568-5317","observed_orcids":["https://orcid.org/0000-0001-8568-5317"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John S. Brownstein","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-8568-5317","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5035052603","display_name":"Naren Ramakrishnan","orcid":"https://orcid.org/0000-0002-1821-9743","observed_orcids":["https://orcid.org/0000-0002-1821-9743"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Naren Ramakrishnan","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-1821-9743","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11819","display_name":"Data-Driven Disease Surveillance","score":0.86080002784729,"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":0.86080002784729,"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/T10028","display_name":"Topic Modeling","score":0.12780000269412994,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.0017000000225380063,"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/disease-surveillance","display_name":"disease surveillance","score":0.7900000214576721},{"id":"https://openalex.org/keywords/domain-specific-word-embeddings","display_name":"domain-specific word embeddings","score":0.8930000066757202},{"id":"https://openalex.org/keywords/word2vec","display_name":"Word2Vec","score":0.8479999899864197},{"id":"https://openalex.org/keywords/disease-classification","display_name":"disease classification","score":0.8190000057220459},{"id":"https://openalex.org/keywords/outbreak-forecasting","display_name":"outbreak forecasting","score":0.8040000200271606},{"id":"https://openalex.org/keywords/social-media","display_name":"social media","score":0.5440000295639038},{"id":"https://openalex.org/keywords/news-sources","display_name":"news sources","score":0.4449999928474426}],"concepts":[{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.9226508140563965},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7936782240867615},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7211855053901672},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.7200776934623718},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6577157974243164},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.6539297699928284},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5440073013305664},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5133282542228699},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.5074266791343689},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47835415601730347},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.44191667437553406},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.38218963146209717},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3658767640590668},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33542460203170776},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.15037038922309875},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2292460057","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1603.00106v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:2292460057","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1603.00106v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[{"score":0.4043000042438507,"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2418017720","https://openalex.org/W2963603716","https://openalex.org/W3035838902","https://openalex.org/W7112446432","https://openalex.org/W2737555350","https://openalex.org/W4289139673","https://openalex.org/W3135017771","https://openalex.org/W3127281840","https://openalex.org/W4376274788","https://openalex.org/W2319972831"],"abstract_inverted_index":{"Traditional":[0],"disease":[1,48,78,115],"surveillance":[2,29],"can":[3],"be":[4],"augmented":[5],"with":[6],"a":[7,47],"wide":[8],"variety":[9],"of":[10,28],"realtime":[11],"sources":[12,21],"such":[13,31],"as":[14,32,63],"news":[15,69],"and":[16,26,35,60,80,117],"social":[17],"media.":[18],"However,":[19],"these":[20,73],"are":[22],"in":[23,109],"general":[24],"unstructured":[25],"construction":[27],"tools":[30],"taxonomical":[33],"correlations":[34],"trace":[36],"mapping":[37],"involves":[38],"considerable":[39],"human":[40,86],"supervision.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45,55],"motivate":[46],"vocabulary":[49],"driven":[50],"word2vec":[51,97],"model":[52,58,83],"(Dis2Vec)":[53],"which":[54],"use":[56,72],"to":[57,76,112],"diseases":[59],"constituent":[61],"attributes":[62,116],"word":[64,74],"embeddings":[65,75],"from":[66],"the":[67],"HealthMap":[68],"corpus.":[70],"We":[71,89],"create":[77],"taxonomies":[79],"evaluate":[81],"our":[82,91],"accuracy":[84],"against":[85,93],"annotated":[87],"taxonomies.":[88],"compare":[90],"accuracies":[92],"several":[94],"state-of-the":[95],"art":[96],"methods.":[98],"Our":[99],"results":[100],"demonstrate":[101],"that":[102],"Dis2Vec":[103],"outperforms":[104],"traditional":[105],"distributed":[106],"vector":[107],"representations":[108],"its":[110],"ability":[111],"faithfully":[113],"capture":[114],"accurately":[118],"forecast":[119],"outbreaks.":[120]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-09-22T06:50:58.402377","created_date":"2016-06-24T00:00:00"}