| fullrecord |
[{"key": "dc.contributor.advisor", "value": "Vuorinen, Jukka", "language": null, "element": "contributor", "qualifier": "advisor", "schema": "dc"}, {"key": "dc.contributor.author", "value": "Mustalahti, Jaakko", "language": null, "element": "contributor", "qualifier": "author", "schema": "dc"}, {"key": "dc.date.accessioned", "value": "2025-05-05T11:19:04Z", "language": null, "element": "date", "qualifier": "accessioned", "schema": "dc"}, {"key": "dc.date.available", "value": "2025-05-05T11:19:04Z", "language": null, "element": "date", "qualifier": "available", "schema": "dc"}, {"key": "dc.date.issued", "value": "2025", "language": null, "element": "date", "qualifier": "issued", "schema": "dc"}, {"key": "dc.identifier.uri", "value": "https://jyx.jyu.fi/handle/123456789/101746", "language": null, "element": "identifier", "qualifier": "uri", "schema": "dc"}, {"key": "dc.description.abstract", "value": "The systematic literature review process is essential for synthesizing existing knowledge and identifying research gaps across various academic fields. However, traditional literature review processes are time-consuming and costly, often requiring substantial manual effort. Despite rapid advancements in artificial intelligence and automation technologies, academic research methodologies, particularly literature reviews, have not fully leveraged these innovations. This study investigates how large language models and automa-tion solutions can enhance the efficiency and reliability of systematic litera-ture reviews while maintaining rigorous academic standards.\nThe research problem focuses on integrating artificial intelligence ena-bled automation into the literature review process. Specifically, the study ex-plores how the usage of large language models can improve the efficiency of selecting and evaluating studies, how a human-in-the-loop approach can miti-gate biases and enhance reliability, and the extent to which automation can improve the accuracy and reproducibility of literature reviews.\nUsing the Design Science Research methodology, this study develops and evaluates the Auto Literature Review artifact, an artificial intelligence enabled tool designed to automate study selection while incorporating human over-sight. The artifact was evaluated against a benchmark systematic literature review in the field of Information Systems. Evaluation results indicate that the artifact achieves classification accuracy comparable or superior to manual re-views while significantly reducing the time and effort required. Additionally, the study highlights that process descriptions in manually compiled literature reviews suffer from inconsistencies and irreproducibility, issues that automa-tion can help mitigate. However, limitations such as full-text paywall re-strictions, potential of bias in operating the artifact, and lack of quantitative evaluation were identified.\nThe findings suggest that automation, when coupled with human over-sight, can enhance the efficiency and reliability of systematic literature re-views. This study contributes to academic research by providing a prototype artifact that demonstrates the potential of large language models in literature review automation while underscoring the importance of maintaining human control over critical decision-making processes. Future research should ex-plore full-text analysis integration, bias mitigation strategies, and novel op-portunities to integrate large language models into research methodologies.", "language": "en", "element": "description", "qualifier": "abstract", "schema": "dc"}, {"key": "dc.description.abstract", "value": "Systemaattiset kirjallisuuskatsaukset ovat keskeisess\u00e4 roolissa olemassa ole-van tiedon koostamisessa ja tutkimusaukkojen tunnistamisessa. Perinteiset kirjallisuuskatsaukset viev\u00e4t kuitenkin paljon aikaa ja ovat kalliita toteuttaa. Teknologian kehityksell\u00e4 on mahdollistava rooli tehostaa ja parantaa n\u00e4it\u00e4 manuaalisia prosesseja, mutta niit\u00e4 ei hy\u00f6dynnet\u00e4 optimaalisella tavalla aka-teemisen tutkimuksen tukena. T\u00e4m\u00e4n vuoksi tutkimus pyrkii selvitt\u00e4m\u00e4\u00e4n, miten suuret kielimallit voivat tehostaa systemaattisia kirjallisuuskatsauksia s\u00e4ilytt\u00e4en tieteelliselle tutkimukselle ominaisen tarkkuuden.\nTutkimusongelmaksi tunnistettiin teko\u00e4lypohjaisen automaation hy\u00f6-dynt\u00e4minen osana kirjallisuuskatsausprosessia. Tutkimuksessa pyrittiin ym-m\u00e4rt\u00e4m\u00e4\u00e4n, kuinka suuret kielimallit voivat tehostaa ja parantaa kirjallisuus-hakua ja -arviointia. Lis\u00e4ksi ihmisen ohjaavaa roolia automaatioprosessissa tarkasteltiin, ja arvioitiin, miss\u00e4 m\u00e4\u00e4rin automaatio voi parantaa tutkimuksen tarkkuutta ja toistettavuutta.\nTutkimuksessa kehitettiin Auto Literature Review -ohjelmisto Design Science -metodologiaa hy\u00f6dynt\u00e4en. Ohjelmiston tarkkuutta arvioitiin toisin-tamalla sill\u00e4 tietoj\u00e4rjestelm\u00e4tieteess\u00e4 julkaistun systemaattisen kirjallisuus-katsauksen hakumenetelm\u00e4. Tulokset osoittivat, ett\u00e4 ohjelmisto saavutti ih-misenkaltaisen tai paremman luokittelutarkkuuden osoittaen mahdollisuu-den prosessin tehostamiseen. Tutkimuksessa havaittiin my\u00f6s, ett\u00e4 alalla ma-nuaalisesti koostetuissa kirjallisuuskatsauksissa on usein ep\u00e4johdonmukaisia prosessikuvauksia, mik\u00e4 hankaloitti objektiivista arviointia. Koska kehitetty ohjelmisto pystyy seuraamaan prosessia t\u00e4sm\u00e4llisesti, esitettiin automaation parantavan raportoinnin toistettavuutta. Rajoitteina havaittiin esimerkiksi haaste analysoida kokonaisia tutkimuksia niiden maksumuurin takia, mah-dollinen ohjelmiston k\u00e4ytt\u00e4j\u00e4n subjektiivinen puolueellisuus ja ohjelmiston kvantitatiivisen arvioinnin puute.\nTutkimustulokset viittaavat, ett\u00e4 ihmisen valvoma automaatioprosessi voi parantaa systemaattisen kirjallisuuskatsauksen tehokkuutta ja luotetta-vuutta. Tutkimus tarjoaa my\u00f6s akateemiselle yhteis\u00f6lle toimivan prototyyp-piohjelmiston, jolla voi tehokkaasti valikoida katsaukselle merkitt\u00e4v\u00e4n kirjal-lisuuden. Lopuksi todettakoon, ett\u00e4 tutkimuksen tulisi tulevaisuudessa keskit-ty\u00e4 suurien kielimallien hy\u00f6dynt\u00e4miseen kokonaisten tutkimusten analy-soinnissa ja selvitt\u00e4\u00e4, miten teko\u00e4ly\u00e4 voisi hy\u00f6dynt\u00e4\u00e4 tutkimusprosesseissa laajemminkin minimoiden subjektiivista puolueellisuutta.", "language": "fi", "element": "description", "qualifier": "abstract", "schema": "dc"}, {"key": "dc.description.provenance", "value": "Submitted by jyx lomake-julkaisija (jyx-julkaisija.group@korppi.jyu.fi) on 2025-05-05T11:19:04Z\nNo. of bitstreams: 0", "language": "en", "element": "description", "qualifier": "provenance", "schema": "dc"}, {"key": "dc.description.provenance", "value": "Made available in DSpace on 2025-05-05T11:19:04Z (GMT). No. of bitstreams: 0", "language": "en", "element": "description", "qualifier": "provenance", "schema": "dc"}, {"key": "dc.format.extent", "value": "70", "language": null, "element": "format", "qualifier": "extent", "schema": "dc"}, {"key": "dc.format.mimetype", "value": "application/pdf", "language": null, "element": "format", "qualifier": "mimetype", "schema": "dc"}, {"key": "dc.language.iso", "value": "eng", "language": null, "element": "language", "qualifier": "iso", "schema": "dc"}, {"key": "dc.rights", "value": "CC BY 4.0", "language": null, "element": "rights", "qualifier": null, "schema": "dc"}, {"key": "dc.title", "value": "Enhancing Efficiency in Systematic Reviews: Automating Study Selection with GPT-4o Model", "language": null, "element": "title", "qualifier": null, "schema": "dc"}, {"key": "dc.type", "value": "master thesis", "language": null, "element": "type", "qualifier": null, "schema": "dc"}, {"key": "dc.identifier.urn", "value": "URN:NBN:fi:jyu-202505053746", "language": null, "element": "identifier", "qualifier": "urn", "schema": "dc"}, {"key": "dc.contributor.faculty", "value": "Informaatioteknologian tiedekunta", "language": "fi", "element": "contributor", "qualifier": "faculty", "schema": "dc"}, {"key": "dc.contributor.faculty", "value": "Faculty of Information Technology", "language": "en", "element": "contributor", "qualifier": "faculty", "schema": "dc"}, {"key": "dc.contributor.organization", "value": "Jyv\u00e4skyl\u00e4n yliopisto", "language": "fi", "element": "contributor", "qualifier": "organization", "schema": "dc"}, {"key": "dc.contributor.organization", "value": "University of Jyv\u00e4skyl\u00e4", "language": "en", "element": "contributor", "qualifier": "organization", "schema": "dc"}, {"key": "dc.subject.discipline", "value": "Tietoj\u00e4rjestelm\u00e4tieteen maisteriohjelma", "language": "fi", "element": "subject", "qualifier": "discipline", "schema": "dc"}, {"key": "dc.subject.discipline", "value": "Master's Degree Programme in Information Systems", "language": "en", "element": "subject", "qualifier": "discipline", "schema": "dc"}, {"key": "dc.type.coar", "value": "http://purl.org/coar/resource_type/c_bdcc", "language": null, "element": "type", "qualifier": "coar", "schema": "dc"}, {"key": "dc.rights.copyright", "value": "\u00a9 The Author(s)", "language": null, "element": "rights", "qualifier": "copyright", "schema": "dc"}, {"key": "dc.rights.accesslevel", "value": "openAccess", "language": null, "element": "rights", "qualifier": "accesslevel", "schema": "dc"}, {"key": "dc.type.publication", "value": "masterThesis", "language": null, "element": "type", "qualifier": "publication", "schema": "dc"}, {"key": "dc.format.content", "value": "fulltext", "language": null, "element": "format", "qualifier": "content", "schema": "dc"}, {"key": "dc.rights.url", "value": "https://creativecommons.org/licenses/by/4.0/", "language": null, "element": "rights", "qualifier": "url", "schema": "dc"}, {"key": "dc.description.accessibilityfeature", "value": "unknown accessibility", "language": "en", "element": "description", "qualifier": "accessibilityfeature", "schema": "dc"}, {"key": "dc.description.accessibilityfeature", "value": "ei tietoa saavutettavuudesta", "language": "fi", "element": "description", "qualifier": "accessibilityfeature", "schema": "dc"}]
|