{"id":"https://openalex.org/W2162317738","doi":"https://doi.org/10.1186/1471-2105-16-s13-s8","title":"A heuristic approach to determine an appropriate number of topics in topic modeling","display_name":"A heuristic approach to determine an appropriate number of topics in topic modeling","publication_year":2015,"publication_date":"2015-09-26","ids":{"openalex":"https://openalex.org/W2162317738","doi":"https://doi.org/10.1186/1471-2105-16-s13-s8","mag":"2162317738","pmid":"https://pubmed.ncbi.nlm.nih.gov/26424364"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-16-s13-s8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-16-s13-s8","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/1471-2105-16-S13-S8","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/1471-2105-16-S13-S8","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079405950","display_name":"Weizhong Zhao","orcid":"https://orcid.org/0000-0001-8552-6084"},"institutions":[{"id":"https://openalex.org/I4610292","display_name":"Xiangtan University","ror":"https://ror.org/00xsfaz62","country_code":"CN","type":"education","lineage":["https://openalex.org/I4610292"]},{"id":"https://openalex.org/I1320320070","display_name":"United States Food and Drug Administration","ror":"https://ror.org/034xvzb47","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1320320070"]},{"id":"https://openalex.org/I1304557061","display_name":"National Center for Toxicological Research","ror":"https://ror.org/05jmhh281","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1304557061","https://openalex.org/I1320320070"]}],"countries":["CN","US"],"is_corresponding":true,"raw_author_name":"Weizhong Zhao","raw_affiliation_strings":["College of Information Engineering, Xiangtan University, Xiangtan, Hunan Province, China","Division of Bioinformatics and Biostatistics, National Center for Toxicological Research, U.S. Food and Drug Administration, Jefferson, AR, 72079, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Engineering, Xiangtan University, Xiangtan, Hunan Province, China","institution_ids":["https://openalex.org/I4610292"]},{"raw_affiliation_string":"Division of Bioinformatics and Biostatistics, National Center for Toxicological Research, U.S. Food and Drug Administration, Jefferson, AR, 72079, USA","institution_ids":["https://openalex.org/I1304557061","https://openalex.org/I1320320070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051461953","display_name":"James J. Chen","orcid":"https://orcid.org/0000-0001-6967-6349"},"institutions":[{"id":"https://openalex.org/I1304557061","display_name":"National Center for Toxicological Research","ror":"https://ror.org/05jmhh281","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1304557061","https://openalex.org/I1320320070"]},{"id":"https://openalex.org/I1320320070","display_name":"United States Food and Drug Administration","ror":"https://ror.org/034xvzb47","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1320320070"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James J Chen","raw_affiliation_strings":["Division of Bioinformatics and Biostatistics, National Center for Toxicological Research, U.S. Food and Drug Administration, Jefferson, AR, 72079, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Bioinformatics and Biostatistics, National Center for Toxicological Research, U.S. Food and Drug Administration, Jefferson, AR, 72079, USA","institution_ids":["https://openalex.org/I1304557061","https://openalex.org/I1320320070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048655816","display_name":"Roger Perkins","orcid":null},"institutions":[{"id":"https://openalex.org/I1320320070","display_name":"United States Food and Drug Administration","ror":"https://ror.org/034xvzb47","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1320320070"]},{"id":"https://openalex.org/I1304557061","display_name":"National Center for Toxicological Research","ror":"https://ror.org/05jmhh281","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1304557061","https://openalex.org/I1320320070"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roger Perkins","raw_affiliation_strings":["Division of Bioinformatics and Biostatistics, National Center for Toxicological Research, U.S. Food and Drug Administration, Jefferson, AR, 72079, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Bioinformatics and Biostatistics, National Center for Toxicological Research, U.S. Food and Drug Administration, Jefferson, AR, 72079, USA","institution_ids":["https://openalex.org/I1304557061","https://openalex.org/I1320320070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100459796","display_name":"Zhichao Liu","orcid":"https://orcid.org/0000-0001-8102-2399"},"institutions":[{"id":"https://openalex.org/I1304557061","display_name":"National Center for Toxicological Research","ror":"https://ror.org/05jmhh281","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1304557061","https://openalex.org/I1320320070"]},{"id":"https://openalex.org/I1320320070","display_name":"United States Food and Drug Administration","ror":"https://ror.org/034xvzb47","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1320320070"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhichao Liu","raw_affiliation_strings":["Division of Bioinformatics and Biostatistics, National Center for Toxicological Research, U.S. Food and Drug Administration, Jefferson, AR, 72079, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Bioinformatics and Biostatistics, National Center for Toxicological Research, U.S. Food and Drug Administration, Jefferson, AR, 72079, USA","institution_ids":["https://openalex.org/I1304557061","https://openalex.org/I1320320070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109700398","display_name":"Weigong Ge","orcid":null},"institutions":[{"id":"https://openalex.org/I1320320070","display_name":"United States Food and Drug Administration","ror":"https://ror.org/034xvzb47","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1320320070"]},{"id":"https://openalex.org/I1304557061","display_name":"National Center for Toxicological Research","ror":"https://ror.org/05jmhh281","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1304557061","https://openalex.org/I1320320070"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weigong Ge","raw_affiliation_strings":["Division of Bioinformatics and Biostatistics, National Center for Toxicological Research, U.S. Food and Drug Administration, Jefferson, AR, 72079, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Bioinformatics and Biostatistics, National Center for Toxicological Research, U.S. Food and Drug Administration, Jefferson, AR, 72079, USA","institution_ids":["https://openalex.org/I1304557061","https://openalex.org/I1320320070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101974769","display_name":"Yijun Ding","orcid":"https://orcid.org/0000-0002-8184-5835"},"institutions":[{"id":"https://openalex.org/I1320320070","display_name":"United States Food and Drug Administration","ror":"https://ror.org/034xvzb47","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1320320070"]},{"id":"https://openalex.org/I1304557061","display_name":"National Center for Toxicological Research","ror":"https://ror.org/05jmhh281","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1304557061","https://openalex.org/I1320320070"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yijun Ding","raw_affiliation_strings":["Division of Bioinformatics and Biostatistics, National Center for Toxicological Research, U.S. Food and Drug Administration, Jefferson, AR, 72079, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Bioinformatics and Biostatistics, National Center for Toxicological Research, U.S. Food and Drug Administration, Jefferson, AR, 72079, USA","institution_ids":["https://openalex.org/I1304557061","https://openalex.org/I1320320070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008241848","display_name":"Wen Zou","orcid":"https://orcid.org/0000-0002-3735-1133"},"institutions":[{"id":"https://openalex.org/I1320320070","display_name":"United States Food and Drug Administration","ror":"https://ror.org/034xvzb47","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1320320070"]},{"id":"https://openalex.org/I1304557061","display_name":"National Center for Toxicological Research","ror":"https://ror.org/05jmhh281","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1304557061","https://openalex.org/I1320320070"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wen Zou","raw_affiliation_strings":["Division of Bioinformatics and Biostatistics, National Center for Toxicological Research, U.S. Food and Drug Administration, Jefferson, AR, 72079, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Bioinformatics and Biostatistics, National Center for Toxicological Research, U.S. Food and Drug Administration, Jefferson, AR, 72079, USA","institution_ids":["https://openalex.org/I1304557061","https://openalex.org/I1320320070"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5079405950"],"corresponding_institution_ids":["https://openalex.org/I1304557061","https://openalex.org/I1320320070","https://openalex.org/I4610292"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":185.6173,"has_fulltext":true,"cited_by_count":390,"citation_normalized_percentile":{"value":0.99955393,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"16","issue":"S13","first_page":"S8","last_page":"S8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.3474999964237213,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.3474999964237213,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.2630000114440918,"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":0.07649999856948853,"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/perplexity","display_name":"Perplexity","score":0.7672443389892578},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7596259117126465},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.6867310404777527},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.6038146018981934},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5807473063468933},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5236444473266602},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5143080949783325},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48441675305366516},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.46034955978393555},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.4328915476799011},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4313850998878479},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4000602066516876},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3587656617164612},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3303070664405823},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.11893251538276672},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10029551386833191}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.7672443389892578},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7596259117126465},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.6867310404777527},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.6038146018981934},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5807473063468933},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5236444473266602},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5143080949783325},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48441675305366516},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.46034955978393555},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.4328915476799011},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4313850998878479},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4000602066516876},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3587656617164612},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3303070664405823},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.11893251538276672},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10029551386833191},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000066506","descriptor_name":"Heuristics","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D000066506","descriptor_name":"Heuristics","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D000066506","descriptor_name":"Heuristics","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1186/1471-2105-16-s13-s8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-16-s13-s8","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/1471-2105-16-S13-S8","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:26424364","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/26424364","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:europepmc.org:3575126","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4597325","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-16-s13-s8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-16-s13-s8","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/1471-2105-16-S13-S8","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1848448201","display_name":null,"funder_award_id":"61202398","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320332163","display_name":"U.S. Food and Drug Administration","ror":"https://ror.org/034xvzb47"},{"id":"https://openalex.org/F4320332382","display_name":"Oak Ridge Institute for Science and Education","ror":"https://ror.org/0526p1y61"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2162317738.pdf","grobid_xml":"https://content.openalex.org/works/W2162317738.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1880262756","https://openalex.org/W1965116275","https://openalex.org/W1995875735","https://openalex.org/W2001082470","https://openalex.org/W2020842694","https://openalex.org/W2089570507","https://openalex.org/W2098157753","https://openalex.org/W2104901100","https://openalex.org/W2107107106","https://openalex.org/W2107743791","https://openalex.org/W2132926880","https://openalex.org/W2134731454","https://openalex.org/W2142572836","https://openalex.org/W2147152072","https://openalex.org/W2158512572","https://openalex.org/W2159849240","https://openalex.org/W4233135949"],"related_works":["https://openalex.org/W2769501189","https://openalex.org/W4315588616","https://openalex.org/W4312773271","https://openalex.org/W2761847515","https://openalex.org/W130869231","https://openalex.org/W2888805565","https://openalex.org/W2962686197","https://openalex.org/W4293734197","https://openalex.org/W4206967254","https://openalex.org/W2131689821"],"abstract_inverted_index":{"BACKGROUND:":[0],"Topic":[1],"modelling":[2,52],"is":[3,46,134,161,208,262],"an":[4,23],"active":[5],"research":[6,96],"field":[7],"in":[8,76,109,136,217,275],"machine":[9],"learning.":[10],"While":[11],"mainly":[12],"used":[13,50],"to":[14,78,92,102,139,210,264,271],"build":[15],"models":[16],"from":[17,201],"unstructured":[18],"textual":[19,193],"data,":[20],"it":[21],"offers":[22],"effective":[24],"means":[25],"of":[26,58,83,107,123,125,145,150,157,159,173,182,215,221,229,252,277],"data":[27,39,224],"mining":[28],"where":[29],"samples":[30],"represent":[31,40],"documents,":[32],"and":[33,67,69,72,171,192,198,226,270],"different":[34,180,223,231],"biological":[35],"endpoints":[36],"or":[37],"omics":[38],"words.":[41],"Latent":[42],"Dirichlet":[43],"Allocation":[44],"(LDA)":[45],"the":[47,80,104,141,148,169,174,212,266],"most":[48,142],"commonly":[49],"topic":[51,129],"method":[53,176,207],"across":[54],"a":[55,110,113,131,155,164,255],"wide":[56],"number":[57,106,144,214,251],"technical":[59],"fields.":[60],"However,":[61],"model":[62,84,111],"development":[63],"can":[64],"be":[65],"arduous":[66,239],"tedious,":[68],"requires":[70],"burdensome":[71],"systematic":[73,243],"sensitivity":[74,244],"studies":[75,245],"order":[77],"find":[79],"best":[81,213],"set":[82],"parameters.":[85],"Often,":[86],"time-consuming":[87],"subjective":[88],"evaluations":[89],"are":[90],"needed":[91,263],"compare":[93],"models.":[94],"Currently,":[95],"has":[97],"yielded":[98],"no":[99],"easy":[100],"way":[101],"choose":[103,211],"proper":[105],"topics":[108,160,216,253],"beyond":[112],"major":[114],"iterative":[115],"approach.":[116],"METHODS":[117],"AND":[118],"RESULTS:":[119],"Based":[120],"on":[121,195],"analysis":[122],"variation":[124],"statistical":[126],"perplexity":[127,151],"during":[128],"modelling,":[130],"heuristic":[132],"approach":[133],"proposed":[135,162,175,205],"this":[137],"study":[138],"estimate":[140],"appropriate":[143],"topics.":[146],"Specifically,":[147],"rate":[149],"change":[152],"(RPC)":[153],"as":[154,163,254],"function":[156],"numbers":[158],"suitable":[165],"selector.":[166],"We":[167,257],"test":[168],"stability":[170],"effectiveness":[172],"for":[177,227],"three":[178,218],"markedly":[179,237],"types":[181],"grounded-truth":[183],"datasets:":[184],"Salmonella":[185],"next":[186],"generation":[187],"sequencing,":[188],"pharmacological":[189],"side":[190],"effects,":[191],"abstracts":[194],"computational":[196],"biology":[197],"bioinformatics":[199],"(TCBB)":[200],"PubMed.":[202],"CONCLUSION:":[203],"The":[204,233],"RPC-based":[206],"demonstrated":[209],"numerical":[219],"experiments":[220],"widely":[222],"types,":[225],"databases":[228],"very":[230],"sizes.":[232],"work":[234],"required":[235],"was":[236],"less":[238],"than":[240],"if":[241],"full":[242],"had":[246],"been":[247],"carried":[248],"out":[249],"with":[250],"parameter.":[256],"understand":[258],"that":[259],"additional":[260],"investigation":[261],"substantiate":[265],"method's":[267],"theoretical":[268],"basis,":[269],"establish":[272],"its":[273],"generalizability":[274],"terms":[276],"dataset":[278],"characteristics.":[279]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":59},{"year":2024,"cited_by_count":50},{"year":2023,"cited_by_count":52},{"year":2022,"cited_by_count":49},{"year":2021,"cited_by_count":53},{"year":2020,"cited_by_count":43},{"year":2019,"cited_by_count":23},{"year":2018,"cited_by_count":27},{"year":2017,"cited_by_count":17},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2026-05-03T08:25:01.440150","created_date":"2025-10-10T00:00:00"}