{"id":"https://openalex.org/W1978000310","doi":"https://doi.org/10.1007/s11192-014-1321-8","title":"Clustering scientific documents with topic modeling","display_name":"Clustering scientific documents with topic modeling","publication_year":2014,"publication_date":"2014-05-05","ids":{"openalex":"https://openalex.org/W1978000310","doi":"https://doi.org/10.1007/s11192-014-1321-8","mag":"1978000310"},"language":"en","primary_location":{"id":"doi:10.1007/s11192-014-1321-8","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11192-014-1321-8","pdf_url":null,"source":{"id":"https://openalex.org/S148561398","display_name":"Scientometrics","issn_l":"0138-9130","issn":["0138-9130","1588-2861"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320108","host_organization_name":"Springer Nature (Netherlands)","host_organization_lineage":["https://openalex.org/P4310320108","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature (Netherlands)","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientometrics","raw_type":"journal-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/A5082108931","display_name":"Chyi-Kwei Yau","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]},{"id":"https://openalex.org/I2800444561","display_name":"Atlanta Technical College","ror":"https://ror.org/01s3vfp47","country_code":"US","type":"education","lineage":["https://openalex.org/I2800444561"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chyi-Kwei Yau","raw_affiliation_strings":["Technology Policy and Assessment Center, Georgia Tech, Atlanta, GA, 30332-0345, USA","Technology Policy and Assessment Center, Georgia Tech, Atlanta, USA"],"affiliations":[{"raw_affiliation_string":"Technology Policy and Assessment Center, Georgia Tech, Atlanta, GA, 30332-0345, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Technology Policy and Assessment Center, Georgia Tech, Atlanta, USA","institution_ids":["https://openalex.org/I2800444561","https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019651281","display_name":"Alan L. Porter","orcid":"https://orcid.org/0000-0002-4520-6518"},"institutions":[{"id":"https://openalex.org/I2800444561","display_name":"Atlanta Technical College","ror":"https://ror.org/01s3vfp47","country_code":"US","type":"education","lineage":["https://openalex.org/I2800444561"]},{"id":"https://openalex.org/I4210133358","display_name":"Search","ror":"https://ror.org/03f78hn46","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210133358"]},{"id":"https://openalex.org/I4210137004","display_name":"OFS (United States)","ror":"https://ror.org/03c0wvm84","country_code":"US","type":"company","lineage":["https://openalex.org/I4210089187","https://openalex.org/I4210137004","https://openalex.org/I4210157335"]},{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alan Porter","raw_affiliation_strings":["Search Technology, Inc., Norcross, GA, 30992, USA","Technology Policy and Assessment Center, Georgia Tech, Atlanta, GA, 30332-0345, USA","Technology Policy and Assessment Center, Georgia Tech, Atlanta, USA","Search Technology, Inc., Norcross, USA"],"affiliations":[{"raw_affiliation_string":"Search Technology, Inc., Norcross, GA, 30992, USA","institution_ids":["https://openalex.org/I4210137004"]},{"raw_affiliation_string":"Technology Policy and Assessment Center, Georgia Tech, Atlanta, GA, 30332-0345, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Technology Policy and Assessment Center, Georgia Tech, Atlanta, USA","institution_ids":["https://openalex.org/I2800444561","https://openalex.org/I130701444"]},{"raw_affiliation_string":"Search Technology, Inc., Norcross, USA","institution_ids":["https://openalex.org/I4210133358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021003477","display_name":"Nils C. Newman","orcid":"https://orcid.org/0000-0003-2717-1267"},"institutions":[{"id":"https://openalex.org/I2802557195","display_name":"United Nations University \u2013 Maastricht Economic and Social Research Institute on Innovation and Technology","ror":"https://ror.org/053zwxr79","country_code":"NL","type":"facility","lineage":["https://openalex.org/I2802557195","https://openalex.org/I4210104502"]},{"id":"https://openalex.org/I4210110745","display_name":"Interaction Institute for Social Change","ror":"https://ror.org/01qyb4t36","country_code":"US","type":"other","lineage":["https://openalex.org/I4210110745"]}],"countries":["NL","US"],"is_corresponding":false,"raw_author_name":"Nils Newman","raw_affiliation_strings":["IISC, Atlanta, GA, 30357, USA","UNU-MERIT, University of Maastricht, Maastricht, Netherlands","IISC, Atlanta, USA"],"affiliations":[{"raw_affiliation_string":"IISC, Atlanta, GA, 30357, USA","institution_ids":["https://openalex.org/I4210110745"]},{"raw_affiliation_string":"UNU-MERIT, University of Maastricht, Maastricht, Netherlands","institution_ids":["https://openalex.org/I2802557195"]},{"raw_affiliation_string":"IISC, Atlanta, USA","institution_ids":["https://openalex.org/I4210110745"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050979764","display_name":"Arho Suominen","orcid":"https://orcid.org/0000-0001-9844-7799"},"institutions":[{"id":"https://openalex.org/I87653560","display_name":"VTT Technical Research Centre of Finland","ror":"https://ror.org/04b181w54","country_code":"FI","type":"nonprofit","lineage":["https://openalex.org/I4210089493","https://openalex.org/I87653560"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Arho Suominen","raw_affiliation_strings":["VTT Technical Research Centre of Finland, Innovations, Economy, and Policy, It\u00e4inen Pitk\u00e4katu 4, P.O. Box 106, 20521, Turku, Finland","VTT Technical Research Centre of Finland, Innovations, Economy, and Policy, Turku, Finland"],"affiliations":[{"raw_affiliation_string":"VTT Technical Research Centre of Finland, Innovations, Economy, and Policy, It\u00e4inen Pitk\u00e4katu 4, P.O. Box 106, 20521, Turku, Finland","institution_ids":["https://openalex.org/I87653560"]},{"raw_affiliation_string":"VTT Technical Research Centre of Finland, Innovations, Economy, and Policy, Turku, Finland","institution_ids":["https://openalex.org/I87653560"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5050979764"],"corresponding_institution_ids":["https://openalex.org/I87653560"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":null,"fwci":12.6858,"has_fulltext":false,"cited_by_count":235,"citation_normalized_percentile":{"value":0.9867574,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"100","issue":"3","first_page":"767","last_page":"786"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9976000189781189,"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"}},"topics":[{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9976000189781189,"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/T10028","display_name":"Topic Modeling","score":0.9961000084877014,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9923999905586243,"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":0.7111853361129761},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6080296039581299},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.6033230423927307},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5263770222663879},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.5127209424972534},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4723074436187744},{"id":"https://openalex.org/keywords/scientific-literature","display_name":"Scientific literature","score":0.41061848402023315},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3246668577194214},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22743916511535645}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7111853361129761},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6080296039581299},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.6033230423927307},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5263770222663879},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.5127209424972534},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4723074436187744},{"id":"https://openalex.org/C2781083858","wikidata":"https://www.wikidata.org/wiki/Q17327049","display_name":"Scientific literature","level":2,"score":0.41061848402023315},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3246668577194214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22743916511535645},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s11192-014-1321-8","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11192-014-1321-8","pdf_url":null,"source":{"id":"https://openalex.org/S148561398","display_name":"Scientometrics","issn_l":"0138-9130","issn":["0138-9130","1588-2861"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320108","host_organization_name":"Springer Nature (Netherlands)","host_organization_lineage":["https://openalex.org/P4310320108","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature (Netherlands)","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientometrics","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:spr:scient:v:100:y:2014:i:3:d:10.1007_s11192-014-1321-8","is_oa":false,"landing_page_url":"http://link.springer.com/10.1007/s11192-014-1321-8","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1447066968","https://openalex.org/W1567401171","https://openalex.org/W1753361524","https://openalex.org/W1880262756","https://openalex.org/W1967884729","https://openalex.org/W1985125789","https://openalex.org/W1995200506","https://openalex.org/W1997439963","https://openalex.org/W2001082470","https://openalex.org/W2003869917","https://openalex.org/W2007508988","https://openalex.org/W2016866273","https://openalex.org/W2024228866","https://openalex.org/W2038939510","https://openalex.org/W2041517243","https://openalex.org/W2042980227","https://openalex.org/W2044764121","https://openalex.org/W2069613886","https://openalex.org/W2072644219","https://openalex.org/W2080534043","https://openalex.org/W2104210067","https://openalex.org/W2107743791","https://openalex.org/W2109154616","https://openalex.org/W2112050062","https://openalex.org/W2118034653","https://openalex.org/W2128925311","https://openalex.org/W2132827946","https://openalex.org/W2154594550","https://openalex.org/W2158266063","https://openalex.org/W2170106220","https://openalex.org/W2200223967","https://openalex.org/W2340222647","https://openalex.org/W2576183678","https://openalex.org/W2612972698","https://openalex.org/W2990138404","https://openalex.org/W3099640513","https://openalex.org/W3119603699","https://openalex.org/W4233135949","https://openalex.org/W4243626155","https://openalex.org/W6639619044","https://openalex.org/W6660743247"],"related_works":["https://openalex.org/W2019737068","https://openalex.org/W2899601636","https://openalex.org/W3015674157","https://openalex.org/W4206655101","https://openalex.org/W4237592971","https://openalex.org/W4309228610","https://openalex.org/W2387982377","https://openalex.org/W4248157169","https://openalex.org/W2002320519","https://openalex.org/W3170128756"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":23},{"year":2023,"cited_by_count":33},{"year":2022,"cited_by_count":30},{"year":2021,"cited_by_count":23},{"year":2020,"cited_by_count":36},{"year":2019,"cited_by_count":19},{"year":2018,"cited_by_count":17},{"year":2017,"cited_by_count":16},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":4}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}