{"id":"https://openalex.org/W6989084526","doi":null,"title":"AI tool for scientific literature data extraction","display_name":"AI tool for scientific literature data extraction","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W6989084526"},"language":"en","primary_location":{"id":"pmh:oai:www.theseus.fi:10024/893515","doi":null,"is_oa":true,"landing_page_url":"http://www.theseus.fi/handle/10024/893515","pdf_url":"http://www.theseus.fi/bitstream/10024/893515/2/Ronkainen_Justiina.pdf","source":{"id":"https://openalex.org/S4306400928","display_name":"Theseus (Ammattikorkeakoulujen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"fi=AMK-opinn\u00e4ytety\u00f6|sv=YH-examensarbete|en=Bachelor's thesis|"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://www.theseus.fi/bitstream/10024/893515/2/Ronkainen_Justiina.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050280443","display_name":"Justiina Ronkainen","orcid":"https://orcid.org/0000-0001-7375-8099","observed_orcids":["https://orcid.org/0000-0001-7375-8099"]},"institutions":[{"id":"https://openalex.org/I63586086","display_name":"Oulu University of Applied Sciences","ror":"https://ror.org/03dvp8k55","country_code":"FI","type":"education","lineage":["https://openalex.org/I63586086"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Ronkainen, Justiina","raw_affiliation_strings":["Oulu University of Applied Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oulu University of Applied Sciences","institution_ids":["https://openalex.org/I63586086"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5050280443"],"corresponding_institution_ids":["https://openalex.org/I63586086"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5609999895095825,"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":0.5609999895095825,"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/T10206","display_name":"Meta-analysis and systematic reviews","score":0.14990000426769257,"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"}},{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.12070000171661377,"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/large-language-models","display_name":"large language models","score":0.7379999756813049},{"id":"https://openalex.org/keywords/systematic-reviews","display_name":"systematic reviews","score":0.7390000224113464},{"id":"https://openalex.org/keywords/meta-analysis","display_name":"meta-analysis","score":0.8240000009536743},{"id":"https://openalex.org/keywords/automatic-data-extraction","display_name":"automated data extraction","score":0.640999972820282},{"id":"https://openalex.org/keywords/prompt-engineering","display_name":"prompt engineering","score":0.7409999966621399},{"id":"https://openalex.org/keywords/langchain","display_name":"LangChain","score":0.6800000071525574},{"id":"https://openalex.org/keywords/gpt-3-5","display_name":"GPT-3.5","score":0.8109999895095825},{"id":"https://openalex.org/keywords/gpt-4","display_name":"GPT-4","score":0.9950000047683716},{"id":"https://openalex.org/keywords/text-chunking","display_name":"text chunking","score":0.6439999938011169}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.715399980545044},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7092000246047974},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6154999732971191},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.5130000114440918},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.5115000009536743},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.507099986076355},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4837999939918518},{"id":"https://openalex.org/C189708586","wikidata":"https://www.wikidata.org/wiki/Q1504425","display_name":"Systematic review","level":3,"score":0.4307999908924103},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39309999346733093},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.3637999892234802},{"id":"https://openalex.org/C2781083858","wikidata":"https://www.wikidata.org/wiki/Q17327049","display_name":"Scientific literature","level":2,"score":0.36010000109672546},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.32710000872612},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.31529998779296875},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2913999855518341},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2700999975204468},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2612000107765198},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.24950000643730164},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.24410000443458557},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.23739999532699585},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.23190000653266907},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2303999960422516},{"id":"https://openalex.org/C157170001","wikidata":"https://www.wikidata.org/wiki/Q4781507","display_name":"Applications of artificial intelligence","level":2,"score":0.2264000028371811},{"id":"https://openalex.org/C63882131","wikidata":"https://www.wikidata.org/wiki/Q17122954","display_name":"Strengths and weaknesses","level":2,"score":0.22349999845027924},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.21400000154972076},{"id":"https://openalex.org/C2983685735","wikidata":"https://www.wikidata.org/wiki/Q5227355","display_name":"Data source","level":2,"score":0.21230000257492065},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.2076999992132187},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.20319999754428864},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2003999948501587},{"id":"https://openalex.org/C178315738","wikidata":"https://www.wikidata.org/wiki/Q603441","display_name":"Bibliometrics","level":2,"score":0.20000000298023224},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.19949999451637268},{"id":"https://openalex.org/C13926793","wikidata":"https://www.wikidata.org/wiki/Q3507155","display_name":"Group method of data handling","level":2,"score":0.1988999992609024},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.19760000705718994},{"id":"https://openalex.org/C174998907","wikidata":"https://www.wikidata.org/wiki/Q357662","display_name":"Work in process","level":2,"score":0.1907999962568283},{"id":"https://openalex.org/C2779965156","wikidata":"https://www.wikidata.org/wiki/Q5227350","display_name":"Data sharing","level":3,"score":0.18930000066757202},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.1882999986410141},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.18770000338554382},{"id":"https://openalex.org/C110326360","wikidata":"https://www.wikidata.org/wiki/Q17149476","display_name":"Metadata modeling","level":4,"score":0.18520000576972961},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.18170000612735748}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:www.theseus.fi:10024/893515","doi":null,"is_oa":true,"landing_page_url":"http://www.theseus.fi/handle/10024/893515","pdf_url":"http://www.theseus.fi/bitstream/10024/893515/2/Ronkainen_Justiina.pdf","source":{"id":"https://openalex.org/S4306400928","display_name":"Theseus (Ammattikorkeakoulujen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"fi=AMK-opinn\u00e4ytety\u00f6|sv=YH-examensarbete|en=Bachelor's thesis|"}],"best_oa_location":{"id":"pmh:oai:www.theseus.fi:10024/893515","doi":null,"is_oa":true,"landing_page_url":"http://www.theseus.fi/handle/10024/893515","pdf_url":"http://www.theseus.fi/bitstream/10024/893515/2/Ronkainen_Justiina.pdf","source":{"id":"https://openalex.org/S4306400928","display_name":"Theseus (Ammattikorkeakoulujen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"fi=AMK-opinn\u00e4ytety\u00f6|sv=YH-examensarbete|en=Bachelor's thesis|"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W6989084526.pdf","grobid_xml":"https://content.openalex.org/works/W6989084526.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W1997684599","https://openalex.org/W2410463469","https://openalex.org/W2626778328","https://openalex.org/W3030163527","https://openalex.org/W3092161080","https://openalex.org/W3120355807","https://openalex.org/W4296977422","https://openalex.org/W4392002118","https://openalex.org/W4392019652","https://openalex.org/W4399616346","https://openalex.org/W4407861126"],"related_works":["https://openalex.org/W7160325224","https://openalex.org/W7139145962","https://openalex.org/W4410157139","https://openalex.org/W6960825784","https://openalex.org/W7103894198","https://openalex.org/W4416201253","https://openalex.org/W4417293488","https://openalex.org/W4406233449","https://openalex.org/W4391423888","https://openalex.org/W4398809873"],"abstract_inverted_index":{"The":[0,81,126],"aim":[1],"of":[2,55,162,185],"this":[3,61],"project":[4,51,82],"was":[5,64,83],"to":[6,21,48,57,65,101,123,144,183],"explore":[7],"artificial":[8],"intelligence":[9],"(AI)":[10],"by":[11],"developing":[12],"a":[13,39,180],"tool":[14],"that":[15,41],"leverages":[16],"large":[17],"language":[18],"models":[19,111],"(LLMs)":[20],"extract":[22,66,146],"structured":[23],"information":[24],"from":[25,150],"scientific":[26,163],"articles.":[27,152],"Systematic":[28],"literature":[29,192],"reviews":[30],"and":[31,46,59,79,89,99,109,114,119,138,171,178],"meta-analyses":[32],"are":[33],"based":[34],"on":[35],"accurate":[36],"data":[37,164],"extraction,":[38],"process":[40],"is":[42],"traditionally":[43],"manual,":[44],"time-consuming":[45],"prone":[47],"mistakes.":[49],"This":[50],"investigated":[52],"the":[53,67,103,151,176,186],"potential":[54,129,172],"LLMs":[56,156],"automate":[58],"streamline":[60],"task.":[62],"Focus":[63],"key":[68],"study":[69,75,139],"elements":[70],"such":[71,134,167],"as":[72,135,168],"article":[73,136],"metadata,":[74],"design,":[76],"statistical":[77],"methods":[78],"results.":[80],"implemented":[84],"using":[85],"Python\u2019s":[86],"LangChain":[87],"framework":[88],"OpenAI":[90],"API.":[91],"Key":[92],"techniques":[93],"included":[94],"prompt":[95],"engineering,":[96],"text":[97],"processing":[98],"chunking":[100],"adapt":[102],"content":[104],"suitable":[105],"for":[106,159],"LLM.":[107],"GPT-3.5":[108],"GPT-4.1":[110],"were":[112],"tested":[113],"evaluated":[115],"against":[116],"each":[117],"other":[118],"human-extracted":[120],"gold":[121],"standard":[122],"assess":[124],"performance.":[125],"model":[127],"demonstrated":[128],"in":[130,190],"extracting":[131],"some":[132],"information,":[133],"metadata":[137],"design;":[140],"however,":[141],"it":[142],"struggled":[143],"reliably":[145],"all":[147],"relevant":[148],"results":[149],"Despite":[153],"current":[154],"limitations,":[155],"hold":[157],"promise":[158],"automating":[160],"aspects":[161],"extraction.":[165],"Improvements":[166],"section-specific":[169],"extraction":[170],"fine-tuning":[173],"may":[174],"enhance":[175],"performance":[177],"offer":[179],"scalable":[181],"solution":[182],"one":[184],"most":[187],"labour-intensive":[188],"steps":[189],"systematic":[191],"review.":[193]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}