{"id":"https://openalex.org/W3004905912","doi":"https://doi.org/10.1109/bibm47256.2019.8983167","title":"Clustering and topic modeling over tweets: A comparison over a health dataset","display_name":"Clustering and topic modeling over tweets: A comparison over a health dataset","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3004905912","doi":"https://doi.org/10.1109/bibm47256.2019.8983167","mag":"3004905912","pmid":"https://pubmed.ncbi.nlm.nih.gov/35463811"},"language":"en","primary_location":{"id":"doi:10.1109/bibm47256.2019.8983167","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm47256.2019.8983167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9028681","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079554685","display_name":"Juan Antonio Lossio-Ventura","orcid":"https://orcid.org/0000-0003-0996-2356"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Juan Antonio Lossio-Ventura","raw_affiliation_strings":["Department of Medicine, Biomedical Informatics, Stanford University, USA"],"affiliations":[{"raw_affiliation_string":"Department of Medicine, Biomedical Informatics, Stanford University, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072426665","display_name":"Juandiego Morz\u00e1n","orcid":null},"institutions":[{"id":"https://openalex.org/I919628346","display_name":"University of the Pacific","ror":"https://ror.org/05mmg7t28","country_code":"PE","type":"education","lineage":["https://openalex.org/I919628346"]}],"countries":["PE"],"is_corresponding":false,"raw_author_name":"Juandiego Morzan","raw_affiliation_strings":["School of Engineering, Universidad del Pac\u00edfico, Lima, Peru"],"affiliations":[{"raw_affiliation_string":"School of Engineering, Universidad del Pac\u00edfico, Lima, Peru","institution_ids":["https://openalex.org/I919628346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079761829","display_name":"Hugo Alatrista-Salas","orcid":"https://orcid.org/0000-0001-5252-4728"},"institutions":[{"id":"https://openalex.org/I919628346","display_name":"University of the Pacific","ror":"https://ror.org/05mmg7t28","country_code":"PE","type":"education","lineage":["https://openalex.org/I919628346"]}],"countries":["PE"],"is_corresponding":false,"raw_author_name":"Hugo Alatrista-Salas","raw_affiliation_strings":["School of Engineering, Universidad del Pac\u00edfico, Lima, Peru"],"affiliations":[{"raw_affiliation_string":"School of Engineering, Universidad del Pac\u00edfico, Lima, Peru","institution_ids":["https://openalex.org/I919628346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023944464","display_name":"Tina Hernandez\u2010Boussard","orcid":"https://orcid.org/0000-0001-6553-3455"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tina Hernandez-Boussard","raw_affiliation_strings":["Department of Medicine, Biomedical Informatics, Stanford University, USA"],"affiliations":[{"raw_affiliation_string":"Department of Medicine, Biomedical Informatics, Stanford University, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030951014","display_name":"Jiang Bian","orcid":"https://orcid.org/0000-0002-2238-5429"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiang Bian","raw_affiliation_strings":["Health Outcomes & Biomedical Informatics, University of Florida, USA"],"affiliations":[{"raw_affiliation_string":"Health Outcomes & Biomedical Informatics, University of Florida, USA","institution_ids":["https://openalex.org/I33213144"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5079554685"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":1.1583,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.79031339,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"2019","issue":null,"first_page":"1544","last_page":"1547"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9933000206947327,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9887999892234802,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8316845893859863},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7700850963592529},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.6907501816749573},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.6662815809249878},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5237483978271484},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.46715134382247925},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4442843198776245},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.42063796520233154},{"id":"https://openalex.org/keywords/health-care","display_name":"Health care","score":0.41794946789741516},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.41057348251342773},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3833759129047394},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2984864115715027},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.27494698762893677},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07237657904624939}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8316845893859863},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7700850963592529},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.6907501816749573},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.6662815809249878},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5237483978271484},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.46715134382247925},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4442843198776245},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42063796520233154},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.41794946789741516},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.41057348251342773},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3833759129047394},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2984864115715027},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.27494698762893677},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07237657904624939},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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":3,"locations":[{"id":"doi:10.1109/bibm47256.2019.8983167","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm47256.2019.8983167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},{"id":"pmid:35463811","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35463811","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":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. IEEE International Conference on Bioinformatics and Biomedicine","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:9028681","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9028681","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings (IEEE Int Conf Bioinformatics Biomed)","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:9028681","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9028681","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings (IEEE Int Conf Bioinformatics Biomed)","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1537829113","https://openalex.org/W1714665356","https://openalex.org/W1880262756","https://openalex.org/W1978394996","https://openalex.org/W1987971958","https://openalex.org/W2016207542","https://openalex.org/W2042980227","https://openalex.org/W2057796125","https://openalex.org/W2085487226","https://openalex.org/W2117756735","https://openalex.org/W2131744502","https://openalex.org/W2147152072","https://openalex.org/W2161163382","https://openalex.org/W2165599843","https://openalex.org/W2250899105","https://openalex.org/W2323015674","https://openalex.org/W2407086192","https://openalex.org/W2489234871","https://openalex.org/W2553110962","https://openalex.org/W2572227972","https://openalex.org/W2751893609","https://openalex.org/W2783885584","https://openalex.org/W2808998506","https://openalex.org/W2809579039","https://openalex.org/W2897464289","https://openalex.org/W2910331986","https://openalex.org/W2913140604","https://openalex.org/W4211258374","https://openalex.org/W6632228503","https://openalex.org/W6639619044","https://openalex.org/W6679775712","https://openalex.org/W6684489972","https://openalex.org/W6691581006"],"related_works":["https://openalex.org/W1795405792","https://openalex.org/W2019737068","https://openalex.org/W2899601636","https://openalex.org/W4254379378","https://openalex.org/W3015674157","https://openalex.org/W4206655101","https://openalex.org/W4237592971","https://openalex.org/W4309228610","https://openalex.org/W4248157169","https://openalex.org/W2387982377"],"abstract_inverted_index":{"Twitter":[0,18,71,110,118],"became":[1],"the":[2,10,31,54,57,64,81,86,143],"most":[3,144],"popular":[4],"form":[5],"of":[6,56,68,80,83,100],"social":[7],"interactions":[8],"in":[9],"healthcare":[11,29],"domain.":[12],"Thus,":[13],"various":[14],"teams":[15],"have":[16,46],"evaluated":[17],"as":[19],"an":[20,94],"additional":[21],"source":[22],"where":[23],"patients":[24],"share":[25],"information":[26],"about":[27],"their":[28,36,148],"with":[30],"potential":[32],"goal":[33],"to":[34,49,63,77,135,141],"improve":[35],"outcomes.":[37],"Several":[38],"existing":[39,87],"topic":[40,102],"modeling":[41,103],"and":[42,66,104,120,130],"document":[43,105],"clustering":[44,106],"applications":[45,58,107],"been":[47],"adapted":[48],"assess":[50],"tweets":[51],"showing":[52],"that":[53,116],"performances":[55],"are":[59],"negatively":[60],"affected":[61],"due":[62],"nature":[65],"characteristics":[67],"tweets.":[69,132],"Moreover,":[70],"health":[72,137],"research":[73],"has":[74],"become":[75],"difficult":[76],"measure":[78],"because":[79],"absence":[82],"comparisons":[84],"between":[85],"applications.":[88],"In":[89],"this":[90,139],"paper,":[91],"we":[92],"perform":[93],"evaluation":[95],"based":[96],"on":[97],"internal":[98],"indexes":[99],"different":[101],"over":[108],"two":[109],"health-related":[111],"datasets.":[112],"Our":[113],"results":[114],"show":[115],"Online":[117],"LDA":[119,122],"Gibbs":[121],"get":[123],"a":[124],"better":[125],"performance":[126],"for":[127,147],"extracting":[128],"topics":[129],"grouping":[131],"We":[133],"want":[134],"provide":[136],"practitioners":[138],"comparison":[140],"select":[142],"suitable":[145],"application":[146],"tasks.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}