{"id":"https://openalex.org/W4403250110","doi":"https://doi.org/10.1007/s41109-024-00658-8","title":"Large language models recover scientific collaboration networks from text","display_name":"Large language models recover scientific collaboration networks from text","publication_year":2024,"publication_date":"2024-10-09","ids":{"openalex":"https://openalex.org/W4403250110","doi":"https://doi.org/10.1007/s41109-024-00658-8"},"language":"en","primary_location":{"id":"doi:10.1007/s41109-024-00658-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41109-024-00658-8","pdf_url":"https://appliednetsci.springeropen.com/counter/pdf/10.1007/s41109-024-00658-8","source":{"id":"https://openalex.org/S3035517252","display_name":"Applied Network Science","issn_l":"2364-8228","issn":["2364-8228"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["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":"Applied Network Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://appliednetsci.springeropen.com/counter/pdf/10.1007/s41109-024-00658-8","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037204886","display_name":"Rathin Jeyaram","orcid":"https://orcid.org/0000-0002-1304-1229"},"institutions":[{"id":"https://openalex.org/I154526488","display_name":"Inserm","ror":"https://ror.org/02vjkv261","country_code":"FR","type":"government","lineage":["https://openalex.org/I154526488"]},{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]},{"id":"https://openalex.org/I4210142324","display_name":"CY Cergy Paris Universit\u00e9","ror":"https://ror.org/043htjv09","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210142324"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Rathin Jeyaram","raw_affiliation_strings":["Learning Planet Institute, Research Unit Learning Transitions (UR LT, joint unit with CY Cergy Paris University), Paris, F-75004, France","Universit\u00e9 Paris Cit\u00e9, Inserm, System Engineering and Evolution Dynamics, Paris, F-75004, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Learning Planet Institute, Research Unit Learning Transitions (UR LT, joint unit with CY Cergy Paris University), Paris, F-75004, France","institution_ids":["https://openalex.org/I4210142324"]},{"raw_affiliation_string":"Universit\u00e9 Paris Cit\u00e9, Inserm, System Engineering and Evolution Dynamics, Paris, F-75004, France","institution_ids":["https://openalex.org/I204730241","https://openalex.org/I154526488"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048213637","display_name":"Robert Ward","orcid":"https://orcid.org/0000-0001-6876-8620"},"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/I4210142324","display_name":"CY Cergy Paris Universit\u00e9","ror":"https://ror.org/043htjv09","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210142324"]},{"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":["FR","US"],"is_corresponding":false,"raw_author_name":"Robert N Ward","raw_affiliation_strings":["Department of Bioengineering, Stanford University, Stanford, CA, USA","Learning Planet Institute, Research Unit Learning Transitions (UR LT, joint unit with CY Cergy Paris University), Paris, F-75004, France","School of Public Policy, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Bioengineering, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Learning Planet Institute, Research Unit Learning Transitions (UR LT, joint unit with CY Cergy Paris University), Paris, F-75004, France","institution_ids":["https://openalex.org/I4210142324"]},{"raw_affiliation_string":"School of Public Policy, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025037098","display_name":"Marc Santolini","orcid":"https://orcid.org/0000-0003-1491-0120"},"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/I154526488","display_name":"Inserm","ror":"https://ror.org/02vjkv261","country_code":"FR","type":"government","lineage":["https://openalex.org/I154526488"]},{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]},{"id":"https://openalex.org/I4210142324","display_name":"CY Cergy Paris Universit\u00e9","ror":"https://ror.org/043htjv09","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210142324"]}],"countries":["FR","US"],"is_corresponding":false,"raw_author_name":"Marc Santolini","raw_affiliation_strings":["Learning Planet Institute, Research Unit Learning Transitions (UR LT, joint unit with CY Cergy Paris University), Paris, F-75004, France","School of Public Policy, Georgia Institute of Technology, Atlanta, GA, USA","Universit\u00e9 Paris Cit\u00e9, Inserm, System Engineering and Evolution Dynamics, Paris, F-75004, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Learning Planet Institute, Research Unit Learning Transitions (UR LT, joint unit with CY Cergy Paris University), Paris, F-75004, France","institution_ids":["https://openalex.org/I4210142324"]},{"raw_affiliation_string":"School of Public Policy, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Universit\u00e9 Paris Cit\u00e9, Inserm, System Engineering and Evolution Dynamics, Paris, F-75004, France","institution_ids":["https://openalex.org/I204730241","https://openalex.org/I154526488"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5037204886"],"corresponding_institution_ids":["https://openalex.org/I154526488","https://openalex.org/I204730241","https://openalex.org/I4210142324"],"apc_list":{"value":790,"currency":"GBP","value_usd":969},"apc_paid":{"value":790,"currency":"GBP","value_usd":969},"fwci":0.7103,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78505189,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"9","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13274","display_name":"Expert finding and Q&A systems","score":0.9955000281333923,"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"}},"topics":[{"id":"https://openalex.org/T13274","display_name":"Expert finding and Q&A systems","score":0.9955000281333923,"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/T10028","display_name":"Topic Modeling","score":0.9926000237464905,"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/T10102","display_name":"scientometrics and bibliometrics research","score":0.9819999933242798,"subfield":{"id":"https://openalex.org/subfields/1804","display_name":"Statistics, Probability and Uncertainty"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.751473069190979},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5949677228927612},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.5471363663673401},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5287898182868958},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5086451768875122},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5076531171798706},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4862914979457855},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.47253134846687317},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4520650804042816},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4387664198875427},{"id":"https://openalex.org/keywords/fuzzy-logic","display_name":"Fuzzy logic","score":0.4246918261051178},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.41663622856140137},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.379546582698822},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37603670358657837},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37041619420051575}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.751473069190979},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5949677228927612},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.5471363663673401},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5287898182868958},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5086451768875122},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5076531171798706},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4862914979457855},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.47253134846687317},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4520650804042816},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4387664198875427},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.4246918261051178},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.41663622856140137},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.379546582698822},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37603670358657837},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37041619420051575},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s41109-024-00658-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41109-024-00658-8","pdf_url":"https://appliednetsci.springeropen.com/counter/pdf/10.1007/s41109-024-00658-8","source":{"id":"https://openalex.org/S3035517252","display_name":"Applied Network Science","issn_l":"2364-8228","issn":["2364-8228"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["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":"Applied Network Science","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-04761340v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04761340","pdf_url":"https://hal.science/hal-04761340/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Applied Network Science, 2024, 9, ⟨10.1007/s41109-024-00658-8⟩","raw_type":"Journal articles"},{"id":"pmh:oai:doaj.org/article:f059d0c67e204a60b4be314a0a6da5cc","is_oa":true,"landing_page_url":"https://doaj.org/article/f059d0c67e204a60b4be314a0a6da5cc","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Applied Network Science, Vol 9, Iss 1, Pp 1-13 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s41109-024-00658-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41109-024-00658-8","pdf_url":"https://appliednetsci.springeropen.com/counter/pdf/10.1007/s41109-024-00658-8","source":{"id":"https://openalex.org/S3035517252","display_name":"Applied Network Science","issn_l":"2364-8228","issn":["2364-8228"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["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":"Applied Network Science","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8156831748","display_name":null,"funder_award_id":"ANR-21-CE38-0002-01","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G8988407266","display_name":null,"funder_award_id":"ANR-21-CE38-0002","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403250110.pdf","grobid_xml":"https://content.openalex.org/works/W4403250110.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W890714660","https://openalex.org/W1970381522","https://openalex.org/W2019020697","https://openalex.org/W2075457132","https://openalex.org/W2081375228","https://openalex.org/W2128918317","https://openalex.org/W2132150998","https://openalex.org/W2748485127","https://openalex.org/W2768062439","https://openalex.org/W2793071066","https://openalex.org/W2803120221","https://openalex.org/W2946021106","https://openalex.org/W2953647140","https://openalex.org/W2979864122","https://openalex.org/W3105859815","https://openalex.org/W3113126806","https://openalex.org/W3121652883","https://openalex.org/W3122140720","https://openalex.org/W3173716597","https://openalex.org/W4226148732","https://openalex.org/W4288593521","https://openalex.org/W4362700315","https://openalex.org/W4379743587","https://openalex.org/W4382202458","https://openalex.org/W4384662964","https://openalex.org/W4387144061","https://openalex.org/W4388184308","https://openalex.org/W4390947766"],"related_works":["https://openalex.org/W2165912799","https://openalex.org/W2735662278","https://openalex.org/W2361861616","https://openalex.org/W2382615723","https://openalex.org/W4311804456","https://openalex.org/W1987484445","https://openalex.org/W2623658258","https://openalex.org/W2143413548","https://openalex.org/W1969219540","https://openalex.org/W2263699433"],"abstract_inverted_index":{"Abstract":[0],"Science":[1],"is":[2],"a":[3,18,80,95,168,172],"collaborative":[4],"endeavor.":[5],"Yet,":[6],"unlike":[7],"co-authorship,":[8],"interactions":[9],"within":[10],"and":[11,43,61,76,103,110],"across":[12],"teams":[13,144,163],"are":[14],"seldom":[15],"reported":[16],"in":[17],"structured":[19],"way,":[20],"making":[21],"them":[22],"hard":[23],"to":[24,59,73,150],"study":[25],"at":[26,89,104,120],"scale.":[27],"We":[28,69],"show":[29],"that":[30,183],"Large":[31,114],"Language":[32,115],"Models":[33,116],"(LLMs)":[34],"can":[35,186],"solve":[36],"this":[37,71],"problem,":[38],"vastly":[39],"improving":[40],"the":[41,90,100,105,133,139,153,159,178],"efficiency":[42],"quality":[44,88],"of":[45,65,82,92,122,137,143,157,180],"network":[46,112],"data":[47],"collection.":[48],"Our":[49],"approach":[50,72,185],"iteratively":[51],"applies":[52],"filtering":[53],"with":[54,125,161],"few-shot":[55],"learning,":[56],"allowing":[57],"us":[58],"identify":[60],"categorize":[62],"different":[63],"types":[64],"relationships":[66],"from":[67,130,145,164],"text.":[68],"compare":[70],"manual":[74],"annotation":[75],"fuzzy":[77,173],"matching":[78,174],"using":[79],"corpus":[81],"digital":[83],"laboratory":[84],"notebooks,":[85],"examining":[86],"inference":[87],"level":[91,107],"edges":[93],"(recovering":[94,99,108],"single":[96],"link),":[97],"labels":[98],"relationship":[101],"context)":[102],"whole-network":[106],"local":[109],"global":[111],"properties).":[113],"perform":[117],"impressively":[118],"well":[119],"each":[121],"these":[123],"tasks,":[124],"edge":[126],"recall":[127],"rate":[128],"ranging":[129],"0.8":[131],"for":[132,152],"highly":[134],"contextual":[135],"case":[136,156],"recovering":[138],"task":[140],"allocation":[141],"structure":[142],"their":[146],"unstructured":[147],"attribution":[148],"page":[149],"0.9":[151],"more":[154],"explicit":[155],"retrieving":[158],"collaboration":[160],"other":[162],"direct":[165],"mentions,":[166],"showing":[167],"32%":[169],"improvement":[170],"over":[171],"approach.":[175],"Beyond":[176],"science,":[177],"flexibility":[179],"LLMs":[181],"means":[182],"our":[184],"be":[187],"extended":[188],"broadly":[189],"through":[190],"minor":[191],"prompt":[192],"revision.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}