Zanda Aivita Cīrule
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zanda Aivita Cīrule has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Anita Jansone
Center for Science and Engineering, RTU Liepaja Academy, LV-3401 Liepaja, Latvia
2 shared publications - Aleksejs Jurenoks
Riga Technical University
1 shared publication - Hans Georg Schaathun
Department of ICT and Natural Sciences, Norwegian University of Science and Technology, NO-6025 Ålesund, Norway
1 shared publication - Lasma Ulmane-Ozolina
Center for Science and Engineering, RTU Liepaja Academy, LV-3401 Liepaja, Latvia
1 shared publication - Natālija Prokofjeva
Faculty of Computer Science, Information Technology and Energy, Riga Technical University, LV-1048 Riga, Latvia
1 shared publication
Latest Publications
- Open Access
Artificial Intelligence-Based Pedagogical Agent in an E-Learning Environment
This study examines the development and pedagogical impact of an AI-based pedagogical agent designed for modern e-learning environments. The research addresses a key challenge in digital education: the lack of personalization and immediate feedback in traditional e-learning systems. AI-driven agents “support and motivate learners through instructional interaction” and provide adaptive, data-driven learning experiences that surpass the limitations of rule-based systems. The study begins with a systematic literature review following PRISMA 2020, analyzing 46 publications from 2020 to 2025 to identify current AI architectures, pedagogical roles, and the empirical evidence of learning impact. The findings highlight the growing use of machine learning, deep learning, multimodal analytics, and large language models in educational agents. These systems perform roles such as tutor, coach, evaluator, dialogue partner, and consultant, offering cognitive, metacognitive, emotional, and analytical support. Modern agents “continuously monitor user interaction, analyze engagement, and adapt learning content”, enabling highly personalized learning pathways. The study also presents the design of a multimodal pedagogical agent capable of explanation, task generation, diagnostics, and adaptive feedback. Experimental results with students (n = 20) show improved performance, reduced errors, and higher engagement when learning with the agent. Overall, the research demonstrates that AI-based pedagogical agents enhance learning effectiveness and support autonomous learning in higher education.
Open AccessArtificial Intelligence-Based Pedagogical Agent in an E-Learning Environment
This study examines the development and pedagogical impact of an AI-based pedagogical agent designed for modern e-learning environments. The research addresses a key challenge in digital education: the lack of personalization and immediate feedback in traditional e-learning systems. AI-driven agents “support and motivate learners through instructional interaction” and provide adaptive, data-driven learning experiences that surpass the limitations of rule-based systems. The study begins with a systematic literature review following PRISMA 2020, analyzing 46 publications from 2020 to 2025 to identify current AI architectures, pedagogical roles, and the empirical evidence of learning impact. The findings highlight the growing use of machine learning, deep learning, multimodal analytics, and large language models in educational agents. These systems perform roles such as tutor, coach, evaluator, dialogue partner, and consultant, offering cognitive, metacognitive, emotional, and analytical support. Modern agents “continuously monitor user interaction, analyze engagement, and adapt learning content”, enabling highly personalized learning pathways. The study also presents the design of a multimodal pedagogical agent capable of explanation, task generation, diagnostics, and adaptive feedback. Experimental results with students (n = 20) show improved performance, reduced errors, and higher engagement when learning with the agent. Overall, the research demonstrates that AI-based pedagogical agents enhance learning effectiveness and support autonomous learning in higher education.
- Open Access
- 6 March 2026
- Published by MDPI AG in Education Sciences
- Vol. 16 (3) , 403
Aspects of University Dropout Criteria Groups: Insights from the Literature
Student dropout in higher education remains a critical issue with far-reaching consequences for students, institutions, and society. This study aims to identify and analyse the criteria influencing student dropout and to propose strategies for improving student retention. A systematic literature review was conducted using the PRISMA 2020 methodology, combined with thematic analysis, to synthesise recent research on academic, financial, behavioural, and personal university climate factors, as well as student attitude factors contributing to dropout. The findings indicate that dropout is a multidimensional and multicausal problem, affected by academic performance, financial challenges, psychological wellbeing, social integration, and institutional environment. Measurable factors, such as grades and attendance, can be used in predictive models and adaptive learning systems, while non-measurable factors, including motivation, engagement, and personal circumstances, inform the targeted student support system model. The study highlights the importance of early identification of at-risk students, holistic support programs, and the integration of both objective and subjective data to enhance student retention. Implementing these strategies can reduce dropout rates, improve student wellbeing, and support sustainable development in higher education. Future research should consider contextual differences across countries and explore adaptive, data-informed support systems to mitigate dropout risks further.
- 6 March 2026
- Published by MDPI AG in Education Sciences
- Vol. 16 (3) , 403
Open AccessAspects of University Dropout Criteria Groups: Insights from the Literature
Student dropout in higher education remains a critical issue with far-reaching consequences for students, institutions, and society. This study aims to identify and analyse the criteria influencing student dropout and to propose strategies for improving student retention. A systematic literature review was conducted using the PRISMA 2020 methodology, combined with thematic analysis, to synthesise recent research on academic, financial, behavioural, and personal university climate factors, as well as student attitude factors contributing to dropout. The findings indicate that dropout is a multidimensional and multicausal problem, affected by academic performance, financial challenges, psychological wellbeing, social integration, and institutional environment. Measurable factors, such as grades and attendance, can be used in predictive models and adaptive learning systems, while non-measurable factors, including motivation, engagement, and personal circumstances, inform the targeted student support system model. The study highlights the importance of early identification of at-risk students, holistic support programs, and the integration of both objective and subjective data to enhance student retention. Implementing these strategies can reduce dropout rates, improve student wellbeing, and support sustainable development in higher education. Future research should consider contextual differences across countries and explore adaptive, data-informed support systems to mitigate dropout risks further.