Please use this identifier to cite or link to this item: https://olympias.lib.uoi.gr/jspui/handle/123456789/40275
Full metadata record
DC FieldValueLanguage
dc.contributor.authorMoustaklis, Christosen
dc.contributor.authorΜουστακλής, Χρήστοςel
dc.date.accessioned2026-07-24T06:20:56Z-
dc.date.available2026-07-24T06:20:56Z-
dc.identifier.urihttps://olympias.lib.uoi.gr/jspui/handle/123456789/40275-
dc.identifier.urihttp://dx.doi.org/10.26268/heal.uoi.19914-
dc.rightsAttribution-NonCommercial-NoDerivs 3.0 United States*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/us/*
dc.subjectPolitical trusten
dc.subjectSocioeconomic inequalitiesen
dc.subjectMachine learningen
dc.subjectLogistic regressionen
dc.subjectRandom foresten
dc.subjectXGBoosten
dc.titleInvestigating socioeconomic inequalities and public attitudes in Europe: evidence from the European values study and World values surveyen
dc.typemasterThesisen
heal.typemasterThesisel
heal.type.enMaster thesisen
heal.type.elΜεταπτυχιακή εργασίαel
heal.classificationSocioeconomicsen
heal.dateAvailable2026-07-24T06:21:56Z-
heal.languageenel
heal.accessfreeel
heal.recordProviderΠανεπιστήμιο Ιωαννίνων. Σχολή Οικονομικών και Διοικητικών Επιστημώνel
heal.publicationDate2026-07-
heal.bibliographicCitationAPAen
heal.abstractPolitical trust constitutes one of the fundamental pillars of democratic governance, influencing institutional legitimacy, political participation and citizens' willingness to comply with public policies. understanding the socioeconomic and political determinants of institutional confidence has therefore become an increasingly important area of research within political science, particularly in the context of growing political polarization, economic inequalities and declining confidence in democratic institutions across. the present study investigates the determinants of political trust by examining citizens' confidence in governments, parliaments and political parties using the harmonized european values study (evs) and world values survey (wvs) dataset. following a comprehensive data preprocessing procedure, three binary classification models—binary logistic regression, random forest and extreme gradient boosting (xgboost)—were implemented to predict institutional confidence. model performance was evaluated using multiple metrics, including accuracy, area under the receiver operating characteristic curve (auc), sensitivity, specificity and precision. furthermore, shapley additive explanations (shap) were employed to enhance model interpretability and identify the most influential predictors of institutional confidence. the empirical findings indicate that satisfaction with democracy, political interest, generalized social trust, age and household income constitute the most important determinants of political trust across all three institutional outcomes. random Forest and xgboost achieved slightly superior predictive performance compared with binary logistic regression; however, all three approaches identified remarkably similar sets of influential variables, demonstrating the robustness of the empirical findings. the integration of explainable machine learning techniques further enhanced the interpretation of complex predictive models while preserving high predictive accuracy. overall, the study demonstrates that political trust is shaped by a multidimensional interaction between socioeconomic characteristics, political attitudes and democratic evaluations. beyond its substantive contribution to the literature on political trust, the research illustrates the value of combining conventional statistical methods with explainable artificial intelligence to improve both predictive performance and model transparency. the findings contribute to the growing field of computational political science and provide evidence that may support the development of evidence-based policies aimed at strengthening democratic legitimacy and institutional confidence within contemporary european democracies.en
heal.advisorNameΝτρίτσος, Γεώργιοςel
heal.committeeMemberNameΝτρίτσος, Γεώργιοςel
heal.committeeMemberNameΓρηγοριάδης, Βασίλειοςel
heal.committeeMemberNameΧαριστός, Κωνσταντίνοςel
heal.academicPublisherΠανεπιστήμιο Ιωαννίνων. Σχολή Οικονομικών και Διοικητικών Επιστημών. Τμήμα Οικονομικών Επιστημώνel
heal.academicPublisherIDuoiel
heal.numberOfPages54el
heal.fullTextAvailabilitytrue-
heal.fullTextAvailabilitytrue-
Appears in Collections:Διατριβές Μεταπτυχιακής Έρευνας (Masters) - ΟΕ

Files in This Item:
File Description SizeFormat 
Μ.Ε. Μουστακλής Χρήστος (2026).pdf1.51 MBAdobe PDFView/Open


This item is licensed under a Creative Commons License Creative Commons