{"id":"https://openalex.org/W4405552797","doi":"https://doi.org/10.1007/s42001-024-00345-9","title":"Open-source LLMs for text annotation: a practical guide for model setting and fine-tuning","display_name":"Open-source LLMs for text annotation: a practical guide for model setting and fine-tuning","publication_year":2024,"publication_date":"2024-12-18","ids":{"openalex":"https://openalex.org/W4405552797","doi":"https://doi.org/10.1007/s42001-024-00345-9","pmid":"https://pubmed.ncbi.nlm.nih.gov/39712076"},"language":"en","primary_location":{"id":"doi:10.1007/s42001-024-00345-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s42001-024-00345-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s42001-024-00345-9.pdf","source":{"id":"https://openalex.org/S4210196583","display_name":"Journal of Computational Social Science","issn_l":"2432-2717","issn":["2432-2717","2432-2725"],"is_oa":false,"is_in_doaj":false,"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":"Journal of Computational Social Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s42001-024-00345-9.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058797533","display_name":"Meysam Alizadeh","orcid":"https://orcid.org/0000-0001-6696-6471"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Meysam Alizadeh","raw_affiliation_strings":["Department of Political Science, University of Zurich, 8050 Zurich, Switzerland","Department of Political Science, University of Zurich, 8050, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0001-6696-6471","affiliations":[{"raw_affiliation_string":"Department of Political Science, University of Zurich, 8050 Zurich, Switzerland","institution_ids":["https://openalex.org/I202697423"]},{"raw_affiliation_string":"Department of Political Science, University of Zurich, 8050, Zurich, Switzerland","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013170605","display_name":"Ma\u00ebl Kubli","orcid":"https://orcid.org/0000-0002-5592-9648"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ma\u00ebl Kubli","raw_affiliation_strings":["Department of Political Science, University of Zurich, 8050 Zurich, Switzerland","Department of Political Science, University of Zurich, 8050, Zurich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Political Science, University of Zurich, 8050 Zurich, Switzerland","institution_ids":["https://openalex.org/I202697423"]},{"raw_affiliation_string":"Department of Political Science, University of Zurich, 8050, Zurich, Switzerland","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000122127","display_name":"Zeynab Samei","orcid":"https://orcid.org/0000-0002-6802-5090"},"institutions":[{"id":"https://openalex.org/I4210146419","display_name":"Institute for Research in Fundamental Sciences","ror":"https://ror.org/04xreqs31","country_code":"IR","type":"facility","lineage":["https://openalex.org/I4210146419"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Zeynab Samei","raw_affiliation_strings":["Department of Computer Science, Institute for Fundamental Research, Tehran, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Institute for Fundamental Research, Tehran, Iran","institution_ids":["https://openalex.org/I4210146419"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018728516","display_name":"Shirin Dehghani","orcid":null},"institutions":[{"id":"https://openalex.org/I200432940","display_name":"Allameh Tabataba'i University","ror":"https://ror.org/02cc4gc68","country_code":"IR","type":"education","lineage":["https://openalex.org/I200432940"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Shirin Dehghani","raw_affiliation_strings":["Department of Computer Engineering, Allameh Tabataba'i University, Tehran, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Allameh Tabataba'i University, Tehran, Iran","institution_ids":["https://openalex.org/I200432940"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106848705","display_name":"Mohammadmasiha Zahedivafa","orcid":null},"institutions":[{"id":"https://openalex.org/I67009956","display_name":"Iran University of Science and Technology","ror":"https://ror.org/01jw2p796","country_code":"IR","type":"education","lineage":["https://openalex.org/I67009956"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Mohammadmasiha Zahedivafa","raw_affiliation_strings":["Department of Computer Science, Iran University of Science and Technology, Tehran, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Iran University of Science and Technology, Tehran, Iran","institution_ids":["https://openalex.org/I67009956"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109620992","display_name":"Juan Diego Bermeo","orcid":"https://orcid.org/0009-0000-6874-4848"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Juan D. Bermeo","raw_affiliation_strings":["Department of Political Science, University of Zurich, 8050 Zurich, Switzerland","Department of Political Science, University of Zurich, 8050, Zurich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Political Science, University of Zurich, 8050 Zurich, Switzerland","institution_ids":["https://openalex.org/I202697423"]},{"raw_affiliation_string":"Department of Political Science, University of Zurich, 8050, Zurich, Switzerland","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008764341","display_name":"Maria Korobeynikova","orcid":null},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Maria Korobeynikova","raw_affiliation_strings":["Department of Political Science, University of Zurich, 8050 Zurich, Switzerland","Department of Political Science, University of Zurich, 8050, Zurich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Political Science, University of Zurich, 8050 Zurich, Switzerland","institution_ids":["https://openalex.org/I202697423"]},{"raw_affiliation_string":"Department of Political Science, University of Zurich, 8050, Zurich, Switzerland","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046475081","display_name":"Fabrizio Gilardi","orcid":"https://orcid.org/0000-0002-0635-3048"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Fabrizio Gilardi","raw_affiliation_strings":["Department of Political Science, University of Zurich, 8050 Zurich, Switzerland","Department of Political Science, University of Zurich, 8050, Zurich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Political Science, University of Zurich, 8050 Zurich, Switzerland","institution_ids":["https://openalex.org/I202697423"]},{"raw_affiliation_string":"Department of Political Science, University of Zurich, 8050, Zurich, Switzerland","institution_ids":["https://openalex.org/I202697423"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5058797533"],"corresponding_institution_ids":["https://openalex.org/I202697423"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":{"value":2290,"currency":"EUR","value_usd":2890},"fwci":16.3602,"has_fulltext":true,"cited_by_count":54,"citation_normalized_percentile":{"value":0.99327863,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"8","issue":"1","first_page":"17","last_page":"17"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9779000282287598,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.9659000039100647,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.7329964637756348},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5436659455299377},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.5407069325447083},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5396243929862976},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3147953748703003},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.1218029260635376},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.07878288626670837}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7329964637756348},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5436659455299377},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.5407069325447083},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5396243929862976},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3147953748703003},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.1218029260635376},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.07878288626670837},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1007/s42001-024-00345-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s42001-024-00345-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s42001-024-00345-9.pdf","source":{"id":"https://openalex.org/S4210196583","display_name":"Journal of Computational Social Science","issn_l":"2432-2717","issn":["2432-2717","2432-2725"],"is_oa":false,"is_in_doaj":false,"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":"Journal of Computational Social Science","raw_type":"journal-article"},{"id":"pmid:39712076","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39712076","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":"Journal of computational social science","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11655591","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11655591","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11655591/pdf/42001_2024_Article_345.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Comput Soc Sci","raw_type":"Text"},{"id":"pmh:doi:10.5167/uzh-266592","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},{"id":"pmh:oai:RePEc:spr:jcsosc:v:8:y:2025:i:1:d:10.1007_s42001-024-00345-9","is_oa":false,"landing_page_url":"http://link.springer.com/10.1007/s42001-024-00345-9","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":{"id":"doi:10.1007/s42001-024-00345-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s42001-024-00345-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s42001-024-00345-9.pdf","source":{"id":"https://openalex.org/S4210196583","display_name":"Journal of Computational Social Science","issn_l":"2432-2717","issn":["2432-2717","2432-2725"],"is_oa":false,"is_in_doaj":false,"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":"Journal of Computational Social Science","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G4066886430","display_name":null,"funder_award_id":"883121","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4730858146","display_name":"Problem Definition in the Digital Democracy","funder_award_id":"883121","funder_id":"https://openalex.org/F4320338335","funder_display_name":"H2020 European Research Council"},{"id":"https://openalex.org/G7842005466","display_name":null,"funder_award_id":"Horizon 2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320323874","display_name":"Universit\u00e4t Z\u00fcrich","ror":"https://ror.org/02crff812"},{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405552797.pdf","grobid_xml":"https://content.openalex.org/works/W4405552797.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W2251617662","https://openalex.org/W2945976633","https://openalex.org/W2963026768","https://openalex.org/W2979691890","https://openalex.org/W3030163527","https://openalex.org/W3034824379","https://openalex.org/W3185341429","https://openalex.org/W4212774754","https://openalex.org/W4226278401","https://openalex.org/W4301183006","https://openalex.org/W4310930460","https://openalex.org/W4319083882","https://openalex.org/W4320165837","https://openalex.org/W4321760789","https://openalex.org/W4361866031","https://openalex.org/W4365512576","https://openalex.org/W4365601444","https://openalex.org/W4366277658","https://openalex.org/W4366733439","https://openalex.org/W4384261711","https://openalex.org/W4384662964","https://openalex.org/W4385570354","https://openalex.org/W4385571411","https://openalex.org/W4386074242","https://openalex.org/W4386102168","https://openalex.org/W4389524317","https://openalex.org/W4389636360","https://openalex.org/W4390947766","https://openalex.org/W4400789854","https://openalex.org/W4402304442","https://openalex.org/W6853251322"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2378211422","https://openalex.org/W2358755282"],"abstract_inverted_index":{"Abstract":[0],"This":[1],"paper":[2],"studies":[3],"the":[4,56,89,166],"performance":[5,52,90],"of":[6,42,64,73,91,138,156,168],"open-source":[7,92,146],"Large":[8],"Language":[9],"Models":[10],"(LLMs)":[11],"in":[12,35,152,170],"text":[13,45,74,157,171],"classification":[14],"tasks":[15,23,76],"typical":[16],"for":[17,44,173],"political":[18],"science":[19],"research.":[20],"By":[21],"examining":[22],"like":[24],"stance,":[25],"topic,":[26],"and":[27,47,67,80,109],"relevance":[28],"classification,":[29],"we":[30,60],"aim":[31],"to":[32,48,96,130],"guide":[33],"scholars":[34],"making":[36],"informed":[37],"decisions":[38],"about":[39],"their":[40],"use":[41],"LLMs":[43,69,147,169],"analysis":[46,84],"establish":[49,125],"a":[50,71,134,153,162],"baseline":[51],"benchmark":[53],"that":[54,86,126,144],"demonstrates":[55],"models\u2019":[57],"effectiveness.":[58],"Specifically,":[59],"conduct":[61],"an":[62],"assessment":[63],"both":[65],"zero-shot":[66,101],"fine-tuned":[68,115,145],"across":[70],"range":[72],"annotation":[75,158,172],"using":[77],"news":[78],"articles":[79],"tweets":[81],"datasets.":[82],"Our":[83,141],"shows":[85],"fine-tuning":[87,127],"improves":[88],"LLMs,":[93],"allowing":[94],"them":[95],"match":[97],"or":[98],"even":[99],"surpass":[100],"GPT":[102,116],"$$-$$":[103,117],"<mml:math":[104,118],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\">":[105,119],"<mml:mo>-</mml:mo>":[106,120],"</mml:math>":[107,121],"3.5":[108],"GPT-4,":[110],"though":[111],"still":[112],"lagging":[113],"behind":[114],"3.5.":[122],"We":[123,160],"further":[124],"is":[128],"preferable":[129],"few-shot":[131],"training":[132],"with":[133],"relatively":[135],"modest":[136],"quantity":[137],"annotated":[139],"text.":[140],"findings":[142],"show":[143],"can":[148],"be":[149],"effectively":[150],"deployed":[151],"broad":[154],"spectrum":[155],"applications.":[159],"provide":[161],"Python":[163],"notebook":[164],"facilitating":[165],"application":[167],"other":[174],"researchers.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":19},{"year":2025,"cited_by_count":33},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-16T09:24:06.705377","created_date":"2025-10-10T00:00:00"}
