{"id":"https://openalex.org/W4416026742","doi":"https://doi.org/10.1007/s11192-025-05445-5","title":"Using language models to label clusters of scientific documents","display_name":"Using language models to label clusters of scientific documents","publication_year":2025,"publication_date":"2025-11-08","ids":{"openalex":"https://openalex.org/W4416026742","doi":"https://doi.org/10.1007/s11192-025-05445-5"},"language":"en","primary_location":{"id":"doi:10.1007/s11192-025-05445-5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11192-025-05445-5","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2511.02601","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069003966","display_name":"Dakota Murray","orcid":"https://orcid.org/0000-0002-7119-0169"},"institutions":[{"id":"https://openalex.org/I113508548","display_name":"Albany State University","ror":"https://ror.org/01vme4277","country_code":"US","type":"education","lineage":["https://openalex.org/I113508548"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dakota Murray","raw_affiliation_strings":["Department of Information Science & Technology, University at Albany, State University of New York, Albany, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-7119-0169","affiliations":[{"raw_affiliation_string":"Department of Information Science & Technology, University at Albany, State University of New York, Albany, NY, USA","institution_ids":["https://openalex.org/I113508548"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022747234","display_name":"Chaoqun Ni","orcid":"https://orcid.org/0000-0002-4130-7602"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chaoqun Ni","raw_affiliation_strings":["Information School, University of Wisconsin - Madison, Madison, WI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information School, University of Wisconsin - Madison, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020630560","display_name":"Weiye Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weiye Gu","raw_affiliation_strings":["Information School, University of Wisconsin - Madison, Madison, WI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information School, University of Wisconsin - Madison, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"last","author":{"id":null,"display_name":"Trevor Hubbard","orcid":null},"institutions":[{"id":"https://openalex.org/I4210110242","display_name":"Digital Science (United States)","ror":"https://ror.org/020h4b682","country_code":"US","type":"company","lineage":["https://openalex.org/I4210110242","https://openalex.org/I4210112888","https://openalex.org/I4210118830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trevor Hubbard","raw_affiliation_strings":["Digital Science, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Digital Science, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210110242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5069003966"],"corresponding_institution_ids":["https://openalex.org/I113508548"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":null,"fwci":0.9597,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.74974944,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"131","issue":"4","first_page":"2303","last_page":"2332"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.23319999873638153,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.23319999873638153,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.11069999635219574,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"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":0.08669999986886978,"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/workflow","display_name":"Workflow","score":0.6852999925613403},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6032999753952026},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5861999988555908},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.491100013256073},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.44940000772476196},{"id":"https://openalex.org/keywords/descriptive-statistics","display_name":"Descriptive statistics","score":0.38119998574256897},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.37929999828338623}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8409000039100647},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6852999925613403},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6032999753952026},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5861999988555908},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5235999822616577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5047000050544739},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.491100013256073},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.44940000772476196},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4341999888420105},{"id":"https://openalex.org/C39896193","wikidata":"https://www.wikidata.org/wiki/Q380344","display_name":"Descriptive statistics","level":2,"score":0.38119998574256897},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.37929999828338623},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.34290000796318054},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3345000147819519},{"id":"https://openalex.org/C142546437","wikidata":"https://www.wikidata.org/wiki/Q2661195","display_name":"Descriptive research","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C166052673","wikidata":"https://www.wikidata.org/wiki/Q83021","display_name":"Empirical evidence","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.27070000767707825}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s11192-025-05445-5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11192-025-05445-5","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:arXiv.org:2511.02601","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.02601","pdf_url":"https://arxiv.org/pdf/2511.02601","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"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":"pmh:oai:arXiv.org:2511.02601","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.02601","pdf_url":"https://arxiv.org/pdf/2511.02601","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"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"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1778510795","display_name":null,"funder_award_id":"2219575","funder_id":"https://openalex.org/F4320332173","funder_display_name":"Directorate for Social, Behavioral and Economic Sciences"},{"id":"https://openalex.org/G7691776356","display_name":"Forging Consensus: A Data-Driven Framework for Studying Scientific Consensus and Debate","funder_award_id":"2219575","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332173","display_name":"Directorate for Social, Behavioral and Economic Sciences","ror":"https://ror.org/03h7mcc28"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4416026742.pdf"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1559665635","https://openalex.org/W1920845339","https://openalex.org/W2059834155","https://openalex.org/W2064498790","https://openalex.org/W2113855231","https://openalex.org/W2116429057","https://openalex.org/W2207112134","https://openalex.org/W2293301714","https://openalex.org/W2592092867","https://openalex.org/W2592745293","https://openalex.org/W2623255526","https://openalex.org/W2888592790","https://openalex.org/W2889326414","https://openalex.org/W2970476646","https://openalex.org/W2970771982","https://openalex.org/W2974135360","https://openalex.org/W3001137683","https://openalex.org/W3017020285","https://openalex.org/W3035324702","https://openalex.org/W3061945531","https://openalex.org/W3119138706","https://openalex.org/W3135345363","https://openalex.org/W4205328242","https://openalex.org/W4238591974","https://openalex.org/W4319074029","https://openalex.org/W4327811957","https://openalex.org/W4384071683","https://openalex.org/W4384300984","https://openalex.org/W4384662964","https://openalex.org/W4385571140","https://openalex.org/W4388488609","https://openalex.org/W4389636360","https://openalex.org/W4391494845","https://openalex.org/W4401042394","https://openalex.org/W4402860127","https://openalex.org/W7084112103"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-07-12T07:33:03.550515","created_date":"2025-11-08T00:00:00"}