{"id":"https://openalex.org/W1975196638","doi":"https://doi.org/10.1145/1882992.1883058","title":"An exploratory study of news article clustering for web-based bio-surveillance","display_name":"An exploratory study of news article clustering for web-based bio-surveillance","publication_year":2010,"publication_date":"2010-11-11","ids":{"openalex":"https://openalex.org/W1975196638","doi":"https://doi.org/10.1145/1882992.1883058","mag":"1975196638"},"language":"en","primary_location":{"id":"doi:10.1145/1882992.1883058","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1882992.1883058","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st ACM International Health Informatics Symposium","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/A5028161578","display_name":"Manabu Torii","orcid":"https://orcid.org/0000-0002-4825-0696"},"institutions":[{"id":"https://openalex.org/I184565670","display_name":"Georgetown University","ror":"https://ror.org/05vzafd60","country_code":"US","type":"education","lineage":["https://openalex.org/I184565670"]},{"id":"https://openalex.org/I2799903593","display_name":"Georgetown University Medical Center","ror":"https://ror.org/00hjz7x27","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799903593"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Manabu Torii","raw_affiliation_strings":["Georgetown University Medical Center, Washington, DC, USA","Georgetown University Medical Center, Washington DC, USA;"],"affiliations":[{"raw_affiliation_string":"Georgetown University Medical Center, Washington, DC, USA","institution_ids":["https://openalex.org/I2799903593","https://openalex.org/I184565670"]},{"raw_affiliation_string":"Georgetown University Medical Center, Washington DC, USA;","institution_ids":["https://openalex.org/I2799903593","https://openalex.org/I184565670"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079981847","display_name":"Burt-Ujin Bayarsaikhan","orcid":null},"institutions":[{"id":"https://openalex.org/I2799903593","display_name":"Georgetown University Medical Center","ror":"https://ror.org/00hjz7x27","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799903593"]},{"id":"https://openalex.org/I184565670","display_name":"Georgetown University","ror":"https://ror.org/05vzafd60","country_code":"US","type":"education","lineage":["https://openalex.org/I184565670"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Burt-Ujin Bayarsaikhan","raw_affiliation_strings":["Georgetown University Medical Center, Washington, DC, USA","Georgetown University Medical Center, Washington DC, USA;"],"affiliations":[{"raw_affiliation_string":"Georgetown University Medical Center, Washington, DC, USA","institution_ids":["https://openalex.org/I2799903593","https://openalex.org/I184565670"]},{"raw_affiliation_string":"Georgetown University Medical Center, Washington DC, USA;","institution_ids":["https://openalex.org/I2799903593","https://openalex.org/I184565670"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101585391","display_name":"Hongfang Liu","orcid":"https://orcid.org/0000-0003-2570-3741"},"institutions":[{"id":"https://openalex.org/I184565670","display_name":"Georgetown University","ror":"https://ror.org/05vzafd60","country_code":"US","type":"education","lineage":["https://openalex.org/I184565670"]},{"id":"https://openalex.org/I2799903593","display_name":"Georgetown University Medical Center","ror":"https://ror.org/00hjz7x27","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799903593"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongfang Liu","raw_affiliation_strings":["Georgetown University Medical Center, Washington, DC, USA","Georgetown University Medical Center, Washington DC, USA;"],"affiliations":[{"raw_affiliation_string":"Georgetown University Medical Center, Washington, DC, USA","institution_ids":["https://openalex.org/I2799903593","https://openalex.org/I184565670"]},{"raw_affiliation_string":"Georgetown University Medical Center, Washington DC, USA;","institution_ids":["https://openalex.org/I2799903593","https://openalex.org/I184565670"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084080635","display_name":"Th\u1eafng Nguy\u1ec5n","orcid":"https://orcid.org/0000-0001-7799-4523"},"institutions":[{"id":"https://openalex.org/I2799903593","display_name":"Georgetown University Medical Center","ror":"https://ror.org/00hjz7x27","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799903593"]},{"id":"https://openalex.org/I184565670","display_name":"Georgetown University","ror":"https://ror.org/05vzafd60","country_code":"US","type":"education","lineage":["https://openalex.org/I184565670"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thang Nguyen","raw_affiliation_strings":["Georgetown University Medical Center, Washington, DC, USA","Georgetown University Medical Center, Washington DC, USA;"],"affiliations":[{"raw_affiliation_string":"Georgetown University Medical Center, Washington, DC, USA","institution_ids":["https://openalex.org/I2799903593","https://openalex.org/I184565670"]},{"raw_affiliation_string":"Georgetown University Medical Center, Washington DC, USA;","institution_ids":["https://openalex.org/I2799903593","https://openalex.org/I184565670"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064883807","display_name":"Kevin T. Jones","orcid":"https://orcid.org/0000-0002-1774-1388"},"institutions":[{"id":"https://openalex.org/I184565670","display_name":"Georgetown University","ror":"https://ror.org/05vzafd60","country_code":"US","type":"education","lineage":["https://openalex.org/I184565670"]},{"id":"https://openalex.org/I2799903593","display_name":"Georgetown University Medical Center","ror":"https://ror.org/00hjz7x27","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799903593"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Jones","raw_affiliation_strings":["Georgetown University Medical Center, Washington, DC, USA","Georgetown University Medical Center, Washington DC, USA;"],"affiliations":[{"raw_affiliation_string":"Georgetown University Medical Center, Washington, DC, USA","institution_ids":["https://openalex.org/I2799903593","https://openalex.org/I184565670"]},{"raw_affiliation_string":"Georgetown University Medical Center, Washington DC, USA;","institution_ids":["https://openalex.org/I2799903593","https://openalex.org/I184565670"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004291388","display_name":"Noele P. Nelson","orcid":"https://orcid.org/0000-0001-9831-0717"},"institutions":[{"id":"https://openalex.org/I184565670","display_name":"Georgetown University","ror":"https://ror.org/05vzafd60","country_code":"US","type":"education","lineage":["https://openalex.org/I184565670"]},{"id":"https://openalex.org/I2799903593","display_name":"Georgetown University Medical Center","ror":"https://ror.org/00hjz7x27","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799903593"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Noele P.> Nelson","raw_affiliation_strings":["Georgetown University Medical Center, Washington, DC, USA","Georgetown University Medical Center, Washington DC, USA;"],"affiliations":[{"raw_affiliation_string":"Georgetown University Medical Center, Washington, DC, USA","institution_ids":["https://openalex.org/I2799903593","https://openalex.org/I184565670"]},{"raw_affiliation_string":"Georgetown University Medical Center, Washington DC, USA;","institution_ids":["https://openalex.org/I2799903593","https://openalex.org/I184565670"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046640393","display_name":"David Hartley","orcid":"https://orcid.org/0000-0003-2589-2538"},"institutions":[{"id":"https://openalex.org/I2799903593","display_name":"Georgetown University Medical Center","ror":"https://ror.org/00hjz7x27","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799903593"]},{"id":"https://openalex.org/I184565670","display_name":"Georgetown University","ror":"https://ror.org/05vzafd60","country_code":"US","type":"education","lineage":["https://openalex.org/I184565670"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David M. Hartley","raw_affiliation_strings":["Georgetown University Medical Center, Washington, DC, USA","Georgetown University Medical Center, Washington DC, USA;"],"affiliations":[{"raw_affiliation_string":"Georgetown University Medical Center, Washington, DC, USA","institution_ids":["https://openalex.org/I2799903593","https://openalex.org/I184565670"]},{"raw_affiliation_string":"Georgetown University Medical Center, Washington DC, USA;","institution_ids":["https://openalex.org/I2799903593","https://openalex.org/I184565670"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5028161578"],"corresponding_institution_ids":["https://openalex.org/I184565670","https://openalex.org/I2799903593"],"apc_list":null,"apc_paid":null,"fwci":0.1856,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58160473,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"435","last_page":"439"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9990000128746033,"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":0.9990000128746033,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9589999914169312,"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"}},{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9495000243186951,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.8436870574951172},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7406692504882812},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.7014418840408325},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4705536663532257},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.4230394661426544},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3703852891921997},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3287356495857239}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8436870574951172},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7406692504882812},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.7014418840408325},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4705536663532257},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.4230394661426544},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3703852891921997},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3287356495857239}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1882992.1883058","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1882992.1883058","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st ACM International Health Informatics Symposium","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Good health and well-being","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/3"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W80963024","https://openalex.org/W1521422465","https://openalex.org/W1532325895","https://openalex.org/W1534018075","https://openalex.org/W1589404549","https://openalex.org/W1651093245","https://openalex.org/W1972787274","https://openalex.org/W2044724262","https://openalex.org/W2079334234","https://openalex.org/W2103235794","https://openalex.org/W2105190739","https://openalex.org/W2116237179","https://openalex.org/W2120467164","https://openalex.org/W2153440002","https://openalex.org/W2155529673","https://openalex.org/W2159181336","https://openalex.org/W2172269818","https://openalex.org/W2272916509","https://openalex.org/W2435251607","https://openalex.org/W2611876886","https://openalex.org/W3169730026","https://openalex.org/W4213009331","https://openalex.org/W4231447289"],"related_works":["https://openalex.org/W4298130764","https://openalex.org/W2804364458","https://openalex.org/W2132641928","https://openalex.org/W4310225030","https://openalex.org/W2090259340","https://openalex.org/W1926736923","https://openalex.org/W2158836806","https://openalex.org/W2393816671","https://openalex.org/W2083665254","https://openalex.org/W2942177010"],"abstract_inverted_index":{"Online":[0],"news":[1],"articles":[2,19],"provide":[3],"rich":[4],"and":[5],"timely":[6],"information":[7],"for":[8],"disease":[9,22],"outbreak":[10],"surveillance.":[11],"Meanwhile,":[12],"it":[13],"is":[14],"not":[15],"trivial":[16],"to":[17,21,42],"search":[18],"relevant":[20],"outbreaks":[23],"among":[24],"the":[25,36,71,79,84,94],"large":[26],"volume":[27],"of":[28,38,59,74,86,105],"online":[29,44],"publications.":[30],"In":[31,89],"this":[32],"study,":[33],"we":[34,56,91],"examined":[35],"use":[37],"text":[39],"clustering":[40,54,95],"techniques":[41],"organize":[43],"articles.":[45],"To":[46],"take":[47],"into":[48],"account":[49],"surveillance":[50],"analysts'":[51],"expertise":[52],"in":[53,63],"articles,":[55],"considered":[57],"selection":[58,73],"informative":[60],"word":[61],"features":[62,75,80,107],"a":[64,102],"supervised":[65,72],"manner.":[66],"Our":[67],"experiments":[68],"suggest":[69],"that":[70,93],"can":[76],"significantly":[77],"reduce":[78],"size":[81],"without":[82],"affecting":[83],"utility":[85],"resulting":[87],"clusters.":[88],"addition,":[90],"observed":[92],"algorithm":[96],"could":[97],"yield":[98],"consistent":[99],"results":[100],"when":[101],"small":[103],"number":[104],"selected":[106],"were":[108],"used.":[109]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}