Messini, S. (2025). Populist Political Communication on Instagram in the 2024 European Elections. Media and Communication, 13. https://www.cogitatiopress.com/mediaandcommunication/article/view/10614/4627
With the rapid rise of social media usage and its integration into daily life, platforms like X (formerly known as Twitter) and Instagram have emerged as essential tools for political communication. Political actors use these platforms to attract voters, exercise opposition to governmental policies, polarize public opinion, and comment on political agendas. This article focuses on the analysis of populist political communication on Instagram by three far-right political leaders—Italian Prime Minister and President of Fratelli d’Italia Giorgia Meloni (European Conservatives and Reformists), President of Elliniki Lysi and Member of Parliament Kyriakos Velopoulos (European Conservatives and Reformists), and the leader of Groupe Rassemblement National and Member of Parliament Marine Le Pen (Patriots for Europe)—during the 2024 European Parliament elections. The analysis centers on three main aspects of Instagram posts: linguistic strategies, thematic content, and audience engagement. Initially, the study examines the linguistic strategies of these politicians, such as the use of simple, comprehensible phrases combined with emotionally charged images. Their posts primarily emphasize nationalist values, cultural identity, and concerns about economic and social stability. Furthermore, the comparative analysis reveals diverse uses of emotionally charged posts, especially during the 2024 pre-election period, with strategies adapting to each nation’s political reality, thus imparting unique characteristics to each campaign. The findings underscore Instagram’s power in shaping political discourse and electoral behavior, highlighting the need for further study of digital communication in modern democracies.
Fanarioti, A. K., & Karpouzis, K. (2025). Artificial Intelligence and the Future of Mental Health in a Digitally Transformed World. Computers, 14(7), 259. https://doi.org/10.3390/computers14070259
Artificial Intelligence (AI) is reshaping mental healthcare by enabling new forms of diagnosis, therapy, and patient monitoring. Yet this digital transformation raises complex policy and ethical questions that remain insufficiently addressed. In this paper, we critically examine how AI-driven innovations are being integrated into mental health systems across different global contexts, with particular attention to governance, regulation, and social justice. The study follows the PRISMA-ScR methodology to ensure transparency and methodological rigor, while also acknowledging its inherent limitations, such as the emphasis on breadth over depth and the exclusion of non-English sources. Drawing on international guidelines, academic literature, and emerging national strategies, it identifies both opportunities, such as improved access and personalized care, and threats, including algorithmic bias, data privacy risks, and diminished human oversight. Special attention is given to underrepresented populations and the risks of digital exclusion. The paper argues for a value-driven approach that centers equity, transparency, and informed consent in the deployment of AI tools. It concludes with actionable policy recommendations to support the ethical implementation of AI in mental health, emphasizing the need for cross-sectoral collaboration and global accountability mechanisms.
Bralee, E., Mostazir, M., Warren, F. C., Newbold, A., Hulme, C., Cranston, T., Karpouzis, K. … & Watkins, E. R. (2025). Brief use of behavioral activation features predicts benefits of self-help app on depression symptoms: Secondary analysis of a selective prevention trial in young people. Journal of Consulting and Clinical Psychology, 93(4), 293. https://psycnet.apa.org/fulltext/2025-94075-003.pdf
Objective: To explore which cognitive behavioral therapy (CBT) self-help app usage predicted depression during a selective prevention trial. Method: A recent controlled trial (ECoWeB-PREVENT) randomized young people aged 16–22, at increased risk for depression because of elevated worry/rumination, negative appraisals, and/or rejection sensitivity but without past or current history of major depression, to apps that provided self-monitoring, self-monitoring plus CBT self-help, or self-monitoring plus emotional competency self-help. Self-help included coping strategies for moment-by-moment use (Tools) and self-learning/planning exercises (Challenges). On the primary outcome (depression, Patient Health Questionnaire-9 [PHQ-9]) at 3-months follow-up (primary endpoint), only the CBT app outperformed self-monitoring. In this secondary analysis, only data from participants who used the CBT or self-monitoring apps at least once were analyzed to test what app use predicted change in depression from baseline to 3 months. Results: Of the original 1,262 participants (79% female), 558 were included (CBT, baseline, n = 273, PHQ-9: M = 7.48, SD = 3.9; 3 months, N = 163, PHQ-9: M = 8.83, SD = 4.92; self-monitoring, baseline, n = 285, PHQ-9: M = 7.45, SD = 4.26; 3 months, N = 183, PHQ-9: M = 7.48, SD = 3.9). Neither total app use, self-monitoring, nor use of Tools predicted change in depression (all ps > .05). Frequency of use of Challenges predicted lower depression symptoms and caseness at 3 months (β = −0.28, 95% CI [−0.53, −0.03], p = .029). Specifically, the use of behavioral activation challenges mediated the effects of the CBT app on depression over 3 months (β = −0.59, 95% CI [−1.13, −0.05], p = .03). Conclusions: Brief psychoeducation about behavioral activation principles in an app may protect young people from depression over 3 months, even when only used once.
Roinioti, E., Cherouvis, S., Filipowicz, S., Addis, A., Chappell, K., & Karpouzis, K. (2025). A scoping review of STEAM policies in Europe. Education Sciences, 15(6), 779. https://www.mdpi.com/2227-7102/15/6/779/pdf?version=1750750703
The Road-STEAMer Horizon Europe Program examines STEAM (Science, Technology, Engineering, Arts, and Mathematics) education policies across Europe, with a specific focus on integrating the arts into traditional STEM disciplines. Through the analysis of open-access repositories, official documents, and stakeholder interviews, this study conducts both a macroanalysis of European policies and a detailed analysis of national initiatives. The research categorizes EU member states into three groups: high-priority countries (Belgium, France, Bulgaria, Finland, and Germany), countries acknowledging the importance of STEAM with partial initiatives, and those in early development stages. Special attention is given to grassroots initiatives. The findings reveal significant variation among member states and affiliated countries, driven by unique national challenges. In many cases, STEM/STEAM programs are closely linked to broader societal issues, such as financial development, digital transition, and social inequalities.
Filahi, Y., Gul, O. M., Elghirani, A., Arican, E., Parlak, I. B., Kadry, S., & Karpouzis, K. (2025). Enhanced E-commerce decision-making through sentiment analysis using machine learning-based approaches and IoT. PloS one, 20(6), e0326744. https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0326744
E-commerce is a vital component of the world economy, providing people with a simple and convenient method for shopping and enabling businesses to expand into new global markets. Improving e-commerce decision-making by utilizing IoT and machine intelligence represents an important area for the impact of these technologies. Our objective is to elevate online shopping to a new level, making it a practical and genuinely delightful experience for customers. Businesses can acquire valuable insights to improve their operations and sales strategies by employing IoT devices to collect customer behavior and preference data and using machine learning (ML) algorithms to analyze them. In addition, companies can make simple recommendations using machine learning on the collected data. Our creative implementation of ML algorithms extends beyond simple recommendations. It also includes demand forecasting, guaranteeing that popular products are constantly in stock, reducing disappointments, and increasing consumer satisfaction. We applied several ML techniques, including logistic regression, Naïve Bayes, Support Vector Machine (SVM), Random Forest (RF), AdaBoosting, Gated Recurrent Unit (GRU), and Long Short-Term Memory (LSTM). AdaBoosting outperformed the deep learning (DL) techniques LSTM and GRU and four ML techniques, logistic regression, Naïve Bayes, SVM, and RF, regarding F1 scores, accuracy, precision, and recall. It achieved an accuracy of 88%, an F1-score of 0.927, precision-1 of 0.908, and the ability of identifying true negatives and true positives (recall-0 and recall-1) of 0.569 and 0.947 respectively. Except for SVM, the other ML techniques did not exhibit much performance difference when using the count vectorizer and TD-IDF vectorizer. This study advances e-commerce capabilities through IoT and machine learning and paves the way for a new era of customer-centric, efficient, and adaptive retail strategies.
Karpouzis, K. (2025). AI, Digital Humanities, and the Legacies of Colonial Power. preprints.org https://www.preprints.org/manuscript/202502.1823/v1
This paper examines the impact of artificial intelligence (AI) on digital humanities through a colonial lens, analyzing how AI can both reinforce and challenge colonial power dynamics. AI tools in digital humanities, such as text mining and language preservation, often perpetuate Western epistemologies and marginalize non-Western perspectives due to biases in data and algorithms. Using case studies, such as the Slave Voyages database and indigenous language preservation projects, this paper highlights AI’s dual role as both a potential perpetuator of colonial legacies and a tool for decolonization. It recommends inclusive AI design, community-driven data governance, and the integration of alternative epistemologies to mitigate AI’s colonial biases and promote more equitable knowledge production.
Karpouzis, K. (2024). Plato’s Shadows in the Digital Cave: Controlling Cultural Bias in Generative AI. Electronics, 13(8), 1457. https://www.mdpi.com/2079-9292/13/8/1457
Generative Artificial Intelligence (AI) systems, like ChatGPT, have the potential to perpetuate and amplify cultural biases embedded in their training data, which are predominantly produced by dominant cultural groups. This paper explores the philosophical and technical challenges of detecting and mitigating cultural bias in generative AI, drawing on Plato’s Allegory of the Cave to frame the issue as a problem of limited and distorted representation. We propose a multifaceted approach combining technical interventions, such as data diversification and culturally aware model constraints, with a deeper engagement with the cultural and philosophical dimensions of the problem. Drawing on theories of extended cognition and situated knowledge, we argue that mitigating AI biases requires a reflexive interrogation of the cultural contexts of AI development and a commitment to empowering marginalized voices and perspectives. We claim that controlling cultural bias in generative AI is inseparable from the larger project of promoting equity, diversity, and inclusion in AI development and governance. By bridging philosophical reflection with technical innovation, this paper contributes to the growing discourse on responsible and inclusive AI, offering a roadmap for detecting and mitigating cultural biases while grappling with the profound cultural implications of these powerful technologies.
Messini, S. (2024). Emotion during election periods: Deciphering Twitter users’ discourse. The Greek Review of Social Research, 67-91. https://ejournals.epublishing.ekt.gr/index.php/ekke/article/view/38500
Within computational political science, a sentiment expressed in social media has been subject to examination about electoral behaviour, more so because of the cases of the successful use of social media by candidates (Obama) or by companies who tried to manipulate public opinion (e.g., the involvement of the Russian Internet Research Agency and Cambridge Analytica in 2016 Presidential Elections in the USA, or of Cambridge Analytica’s to the UK’s Referendum about Brexit). In this paper we examine a refinement of analysis, moving from sentiment (positive-negative) to emotions, combine opinion mining with social network analysis, and apply it to the tweets posted during the critical elections that took place in Greece in 2015 and 2019. We find support for the relation between some emotions and voting behaviour in other countries but also realize that the intensity of expressing such emotions is perhaps a better indicator of the need for change.
Karpouzis, K., Pantazatos, D., Taouki, J., & Meli, K. (2024). Tailoring Education with GenAI: A New Horizon in Lesson Planning. arXiv preprint arXiv:2403.12071. https://arxiv.org/abs/2403.12071
The advent of Generative AI (GenAI) in education presents a transformative approach to traditional teaching methodologies, which often overlook the diverse needs of individual students. This study introduces a GenAI tool, based on advanced natural language processing, designed as a digital assistant for educators, enabling the creation of customized lesson plans. The tool utilizes an innovative feature termed ‘interactive mega-prompt,’ a comprehensive query system that allows educators to input detailed classroom specifics such as student demographics, learning objectives, and preferred teaching styles. This input is then processed by the GenAI to generate tailored lesson plans. To evaluate the tool’s effectiveness, a comprehensive methodology incorporating both quantitative (i.e., % of time savings) and qualitative (i.e., user satisfaction) criteria was implemented, spanning various subjects and educational levels, with continuous feedback collected from educators through a structured evaluation form. Preliminary results show that educators find the GenAI-generated lesson plans effective, significantly reducing lesson planning time and enhancing the learning experience by accommodating diverse student needs. This AI-driven approach signifies a paradigm shift in education, suggesting its potential applicability in broader educational contexts, including special education needs (SEN), where individualized attention and specific learning aids are paramount
Skarpelos, Y., Messini, S., Roinioti, E., Karpouzis, K., Kaperonis, S., & Marazoti, M. G. (2024). Emotions during the Pandemic’s First Wave: The Case of Greek Tweets. Digital, 4(1), 126-151. https://www.mdpi.com/2673-6470/4/1/6.
While most published research on COVID-19 focused on a few countries and especially on the second wave of the pandemic and the vaccination period, we turn to the first wave (March–May 2020) to examine the sentiments and emotions expressed by Twitter users in Greece. Using deep-learning techniques, the analysis reveals a complex interplay of surprise, anger, fear, and sadness. Initially, surprise was dominant, reflecting the shock and uncertainty accompanying the sudden onset of the pandemic. Anger replaced surprise as individuals struggled with isolation and social distancing. Despite these challenges, positive sentiments of hope, resilience and solidarity were also expressed. The COVID-19 pandemic had a strong imprint upon the emotional landscape worldwide and in Greece. This calls for appealing to emotions as well as to reason when crafting effective public health strategies.
Panagopoulou, F., Parpoula, C., & Karpouzis, K. (2023). Legal and ethical considerations regarding the use of ChatGPT in education. arXiv preprint arXiv:2306.10037.
Artificial intelligence has evolved enormously over the last two decades, becoming mainstream in different scientific domains including education, where so far, it is mainly utilized to enhance administrative and intelligent tutoring systems services and academic support. ChatGPT, an artificial intelligence-based chatbot, developed by OpenAI and released in November 2022, has rapidly gained attention from the entire international community for its impressive performance in generating comprehensive, systematic, and informative human-like responses to user input through natural language processing. Inevitably, it has also rapidly posed several challenges, opportunities, and potential issues and concerns raised regarding its use across various scientific disciplines. This paper aims to discuss the legal and ethical implications arising from this new technology, identify potential use cases, and enrich our understanding of Generative AI, such as ChatGPT, and its capabilities in education.
Chiotaki, D., Poulopoulos, V., & Karpouzis, K. (2023). Adaptive game-based learning in education: a systematic review. Frontiers in Computer Science, 5, 1062350. https://doi.org/10.3389/fcomp.2023.1062350
The advent and abundance of mobile devices and network connectivity have provided learners of all ages with access to potentially unlimited sources of educational material, from pre-school activities to conventional and after-school courses and continuing education. One of the challenges that learners face is how to locate and access interesting contents suited to their preferences and, more importantly, to the level of expertise and individual needs. From the point of view of content creators and educators, adapting the content and the experience to each learner usually leads to better user retention and a more meaningful and deeper learning experience. In this study, we utilized the PRISMA review methodology to examine research on content and experience adaptivity in educational contexts and report on the authors’ findings. Consisting of well-defined steps (keyword-based retrieval, study scope definition, result filtering, and grouping and analysis), the systematic nature of this methodology ensures its objectivity and replicability at a future stage or replicated by other researchers.
Roinioti, E., Pandia, E., Konstantakis, M., & Skarpelos, Y. (2022). Gamification in Tourism: A Design Framework for the TRIPMENTOR Project. Digital, 2(2), 191-205. DOI: 10.3390/digital2020012
In this paper, we discuss the gamification strategies and methodologies used by TRIPMENTOR—a game-oriented cultural tourism application in the region of Attica. Its primary purpose is to provide visitors with rich media content via the web and mobile environments by redirecting travellers, highlighting points of interest, and providing information for tour operators. Gamification is a critical component of the project; it relates users to specific sites and activities, improves their visiting experiences, and encourages a constant interaction with the application through a playful experience. In TRIPMENTOR, gamification serves both as a tourism marketing strategy and as a tool for encouraging users to share their experiences while exploring Attica in a way designed to meet their personal needs, interests, and habits. This paper aims to describe and analyse the gamification mechanisms applied, following the Octalysis framework, and discuss the opportunities and challenges of gamification as a tourist marketing strategy.Karpouzis, K., Kaperonis, S., & Skarpelos, Y. (2022). Identification of Common Trends in Political Speech in Social Media using Sentiment Analysis. arXiv preprint https://doi.org/10.48550/arXiv.2210.07600.
Social Media have been extensively used for commercial and political communication, besides their initial scope of providing an easy-to-use outlet to produce and consume user-generated content. Besides being a popular medium, Social Media have definitely changed the way we express ourselves or where we look for emerging news and commentary, especially during troubled times. In this paper, we examine a corpus assembled from the Twitter accounts of politicians in the United States and annotated with respect to their audience and the sentiment they convey with each post. Our purpose is to examine whether there are stylistic differences among representatives of different political ideologies, directed to different audiences or with dissimilar agendas. Our findings verify existing knowledge from conventional written communication and can be used to evaluate the quality and depth of political expression and dialogue, especially during the period leading to an election.Menychtas, A., Galliakis, M., Pardos, A., Panagopoulos, C., Karpouzis, K., & Maglogiannis, I. (2022). Gameful Design of an Application for Patients in Rehabilitation. Frontiers in Computer Science, 4, 822167. https://doi.org/10.3389/fcomp.2022.822167
The design process of any interactive application is an important part of its lifecycle, since it largely defines its structure, means of interaction with the users and its actual content. In the case of applications related to medical uses and self-help, it is even more important, given the aims of the application, the diversity of target users and the urgent need for increased retention. In this article, we present a gameful design process for a mobile application targeted toward patients in rehabilitation, implementing concepts related to increasing user rapport and motivation through gamification, and means to offer guidance and personalized services to improve user experience. Both gamification and personalization build on narrative concepts, by putting patients in the place of a “hero”, offering them the opportunity to overcome “challenges” and receive a clear view of their progress (a.k.a. a “hero’s journey”), both in terms of physical and mental condition. Finally, we discuss measurable indicators used to evaluate the application in terms of the progress that patients showed, their motivation and interest, and degree of adherence to the exercise plans.
Roinioti, E. (2020). Caught in the war against gambling: A critical analysis of law history and policy making in video games in Greece. Journal of Greek Media & Culture, 6(2), 261-278. DOI: 10.1386/jgmc_00016_1
The advent of the video game industry brought about new cultural policies in both the national and international levels. In particular, incentives and flexible funding programmes for the production of video games have become a key pillar of support for small, domestic, but also global game companies. In Greece, video game policy history has followed the developments and legal entanglements of gambling regulation, with serious national and international consequences. From the Royal Decree of 1971 to Law 3037/2002 that banned all games in public and private places until the most recent Law 4487/2017, which established a cash rebate scheme for audio-visual productions, this article aims to analyse Greece’s video game policy-making as captured through scattered laws, media articles and personal testimonies.Skarpelos, Y. (2017). Videogames and art edited by Andy Clarke and Grethe Mitchell. Visual Studies, 32(1), 82-83. DOI: 10.1080/1472586X.2016.1271025
