Publications

@article{wang_enhancing_2025,

title = {Enhancing self-regulated learning and higher-order thinking skills in virtual reality: the impact of ChatGPT-integrated feedback aids},

author = {W. -S. Wang and C. -J. Lin and H. -Y. Lee and Y. -M. Huang and T. -T. Wu},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-105002253324&doi=10.1007%2fs10639-025-13557-x&partnerID=40&md5=d737f7160ecfb478201b4f1f960031e4},

doi = {10.1007/s10639-025-13557-x},

issn = {13602357 (ISSN)},

year  = {2025},

date = {2025-01-01},

journal = {Education and Information Technologies},

abstract = {This study explores the integration of ChatGPT technology into Virtual Reality (VR) learning environments to support self-regulated learning (SRL) strategies and foster higher-order thinking skills (HOTS). Utilizing a randomized controlled trial (RCT) design, 81 undergraduate students were randomly assigned to either an experimental group with GPT-feedback-supported VR learning or a control group with traditional feedback-supported VR learning. The VR learning environment focused on embedded IoT tasks, structured into six learning units aligned with Bloom’s taxonomy. Results indicate that the experimental group demonstrated significantly higher cognitive levels across memory, understanding, and application tasks compared to the control group. Notably, GPT feedback markedly improved problem-solving and critical thinking skills, though its impact on creativity was limited. This limitation may be attributed to the directive nature of GPT feedback or the structured scope of learning tasks, which may not have encouraged open-ended creative exploration. SRL abilities were also significantly improved in the experimental group, highlighting the efficacy of GPT feedback in promoting self-reflection, goal setting, and strategy adjustment. The findings underscore the potential of integrating generative AI technologies like ChatGPT into VR learning environments to provide targeted, real-time feedback, thus addressing limitations of traditional VR feedback mechanisms. This integration supports deeper engagement and more effective learning outcomes, particularly in problem-solving and critical thinking, providing valuable insights for future educational technology implementations. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.},

keywords = {ChatGPT, Cognitive levels, feedback mechanisms, Higher-order thinking skills, Self-regulated learning, Virtual Reality},

pubstate = {published},

tppubtype = {article}

}

@article{alibrahim_ai_2025,

title = {AI speechbots and 3D segmentations in virtual reality improve radiology on-call training in resource-limited settings},

author = {Y. Alibrahim and M. Ibrahim and D. Gurdayal and M. Munshi},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-105001472313&doi=10.1016%2fj.ibmed.2025.100245&partnerID=40&md5=623a0ceaa07e5516a296420d25c3033b},

doi = {10.1016/j.ibmed.2025.100245},

issn = {26665212 (ISSN)},

year  = {2025},

date = {2025-01-01},

journal = {Intelligence-Based Medicine},

volume = {11},

abstract = {Objective: Evaluate the use of large-language model (LLM) speechbot tools and deep learning-assisted generation of 3D reconstructions when integrated in a virtual reality (VR) setting to teach radiology on-call topics to radiology residents. Methods: Three first year radiology residents in Guyana were enrolled in an 8-week radiology course that focused on preparation for on-call duties. The course, delivered via VR headsets with custom software integrating LLM-powered speechbots trained on imaging reports and 3D reconstructions segmented with the help of a deep learning model. Each session focused on a specific radiology area, employing a didactic and case-based learning approach, enhanced with 3D reconstructions and an LLM-powered speechbot. Post-session, residents reassessed their knowledge and provided feedback on their VR and LLM-powered speechbot experiences. Results/discussion: Residents found that the 3D reconstructions segmented semi-automatically by deep learning algorithms and AI-driven self-learning via speechbot was highly valuable. The 3D reconstructions, especially in the interventional radiology session, were helpful and the benefit is augmented by VR where navigating the models is seamless and perception of depth is pronounced. Residents also found conversing with the AI-speechbot seamless and was valuable in their post session self-learning. The major drawback of VR was motion sickness, which was mild and improved over time. Conclusion: AI-assisted VR radiology education could be used to develop new and accessible ways of teaching a variety of radiology topics in a seamless and cost-effective way. This could be especially useful in supporting radiology education remotely in regions which lack local radiology expertise. © 2025},

keywords = {3D segmentation, AI speechbots, Article, artificial intelligence chatbot, ChatGPT, computer assisted tomography, Deep learning, headache, human, Image segmentation, interventional radiology, Large language model, Likert scale, nausea, Proof of concept, prospective study, radiology, radiology on call training, resource limited setting, Teaching, Training, ultrasound, Virtual Reality, voice recognition},

pubstate = {published},

tppubtype = {article}

}

@article{gao_pervrml_2025,

title = {PerVRML: ChatGPT-Driven Personalized VR Environments for Machine Learning Education},

author = {H. Gao and Y. Xie and E. Kasneci},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-105005776517&doi=10.1080%2f10447318.2025.2504188&partnerID=40&md5=c2c59be3d20d02c6df7750c2330c8f6d},

doi = {10.1080/10447318.2025.2504188},

issn = {10447318 (ISSN)},

year  = {2025},

date = {2025-01-01},

journal = {International Journal of Human-Computer Interaction},

abstract = {The advent of large language models (LLMs) such as ChatGPT has demonstrated significant potential for advancing educational technologies. Recently, growing interest has emerged in integrating ChatGPT with virtual reality (VR) to provide interactive and dynamic learning environments. This study explores the effectiveness of ChatGTP-driven VR in facilitating machine learning education through PerVRML. PerVRML incorporates a ChatGPT-powered avatar that provides real-time assistance and uses LLMs to personalize learning paths based on various sensor data from VR. A between-subjects design was employed to compare two learning modes: personalized and non-personalized. Quantitative data were collected from assessments, user experience surveys, and interaction metrics. The results indicate that while both learning modes supported learning effectively, ChatGPT-powered personalization significantly improved learning outcomes and had distinct impacts on user feedback. These findings underscore the potential of ChatGPT-enhanced VR to deliver adaptive and personalized educational experiences. © 2025 Taylor & Francis Group, LLC.},

keywords = {Backpropagation, ChatGPT, Curricula, Educational robots, Immersive learning, Interactive learning, Language Model, Large language model, large language models, Learning mode, Machine learning education, Machine-learning, Personalized learning, Support vector machines, Teaching, Virtual Reality, Virtual-reality environment, Virtualization},

pubstate = {published},

tppubtype = {article}

}

@article{ivanova_unveiling_2024,

title = {Unveiling Insights: A Bibliometric Analysis of Artificial Intelligence in Teaching},

author = {M. Ivanova and G. Grosseck and C. Holotescu},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85188949348&doi=10.3390%2finformatics11010010&partnerID=40&md5=aaf44928fb594e2807234da0f3799437},

doi = {10.3390/informatics11010010},

issn = {22279709 (ISSN)},

year  = {2024},

date = {2024-01-01},

journal = {Informatics},

volume = {11},

number = {1},

abstract = {The penetration of intelligent applications in education is rapidly increasing, posing a number of questions of a different nature to the educational community. This paper is coming to analyze and outline the influence of artificial intelligence (AI) on teaching practice which is an essential problem considering its growing utilization and pervasion on a global scale. A bibliometric approach is applied to outdraw the “big picture” considering gathered bibliographic data from scientific databases Scopus and Web of Science. Data on relevant publications matching the query “artificial intelligence and teaching” over the past 5 years have been researched and processed through Biblioshiny in R environment in order to establish a descriptive structure of the scientific production, to determine the impact of scientific publications, to trace collaboration patterns and to identify key research areas and emerging trends. The results point out the growth in scientific production lately that is an indicator of increased interest in the investigated topic by researchers who mainly work in collaborative teams as some of them are from different countries and institutions. The identified key research areas include techniques used in educational applications, such as artificial intelligence, machine learning, and deep learning. Additionally, there is a focus on applicable technologies like ChatGPT, learning analytics, and virtual reality. The research also explores the context of application for these techniques and technologies in various educational settings, including teaching, higher education, active learning, e-learning, and online learning. Based on our findings, the trending research topics can be encapsulated by terms such as ChatGPT, chatbots, AI, generative AI, machine learning, emotion recognition, large language models, convolutional neural networks, and decision theory. These findings offer valuable insights into the current landscape of research interests in the field. © 2024 by the authors.},

keywords = {Artificial intelligence, ChatGPT, Intelligent Environment, large language models, learning analytics, Teaching},

pubstate = {published},

tppubtype = {article}

}

@article{xu_augmented_2024,

title = {Augmented Reality for Maintenance Tasks with ChatGPT for Automated Text-To-Action},

author = {F. Xu and T. Nguyen and J. Du},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85183669638&doi=10.1061%2fJCEMD4.COENG-14142&partnerID=40&md5=6b02d2f4f6e74a8152adf2eb30ee2d88},

doi = {10.1061/JCEMD4.COENG-14142},

issn = {07339364 (ISSN)},

year  = {2024},

date = {2024-01-01},

journal = {Journal of Construction Engineering and Management},

volume = {150},

number = {4},

abstract = {Advancements in sensor technology, artificial intelligence (AI), and augmented reality (AR) have unlocked opportunities across various domains. AR and large language models like GPT have witnessed substantial progress and increasingly are being employed in diverse fields. One such promising application is in operations and maintenance (OM). OM tasks often involve complex procedures and sequences that can be challenging to memorize and execute correctly, particularly for novices or in high-stress situations. By combining the advantages of superimposing virtual objects onto the physical world and generating human-like text using GPT, we can revolutionize OM operations. This study introduces a system that combines AR, optical character recognition (OCR), and the GPT language model to optimize user performance while offering trustworthy interactions and alleviating workload in OM tasks. This system provides an interactive virtual environment controlled by the Unity game engine, facilitating a seamless interaction between virtual and physical realities. A case study (N=30) was conducted to illustrate the findings and answer the research questions. The Multidimensional Measurement of Trust (MDMT) was applied to understand the complexity of trust engagement with such a human-like system. The results indicate that users can complete similarly challenging tasks in less time using our proposed AR and AI system. Moreover, the collected data also suggest a reduction in cognitive load when executing the same operations using the AR and AI system. A divergence of trust was observed concerning capability and ethical dimensions. © 2024 American Society of Civil Engineers.},

keywords = {Artificial intelligence systems, Augmented Reality, Augmented Reality (AR), ChatGPT, Complex sequences, Computational Linguistics, Diverse fields, Human like, Language Model, Maintenance, Maintenance tasks, Operations and maintenance, Optical character recognition, Sensor technologies, Virtual Reality},

pubstate = {published},

tppubtype = {article}

}

@article{jauhiainen_metaverse_2024,

title = {The Metaverse: Innovations and generative AI},

author = {J. S. Jauhiainen},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85195444798&doi=10.1016%2fj.ijis.2024.04.004&partnerID=40&md5=c87978a98d9dab5df74c83a2d5b3626b},

doi = {10.1016/j.ijis.2024.04.004},

issn = {20962487 (ISSN)},

year  = {2024},

date = {2024-01-01},

journal = {International Journal of Innovation Studies},

volume = {8},

number = {3},

pages = {262–272},

abstract = {Today, the Metaverse consists of various platforms, including digital twins of the physical world as well as virtual and blended digital-material environments that offer immersive experiences for individual users. By going beyond solely physical or virtual realms, these platforms unlock new possibilities for exploration, experimentation, and interaction. This makes it possible to transcend the limitations of innovation processes confined to physical locations, so the Metaverse is thus poised to drive groundbreaking innovations. This article explores the Metaverse as an innovation platform, its opportunities and challenges, including the role of generative AI in it. It discusses how the Metaverse, as a collaboration, creativity, and technological platform, supports innovation potential. By embracing the possibilities and challenges offered by the Metaverse and leveraging the capabilities of generative AI within it, a future in which individuals can truly explore novel synergies between the physical and digital realms, thriving various kinds of innovations. It is crucial to achieve holistic sustainability impacts both within the Metaverse innovation platform and as its outputs. © 2024 China Science Publishing & Media Ltd},

keywords = {ChatGPT, Collaboration, Creativity, Generative AI, Innovation, Metaverse, Sustainability},

pubstate = {published},

tppubtype = {article}

}

@article{hubal_rethinking_2024,

title = {Rethinking some Virtual Human Applications},

author = {R. Hubal},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85215435480&partnerID=40&md5=4526a7d54606ef0f1cc6234099eb4aae},

issn = {15548716 (ISSN)},

year  = {2024},

date = {2024-01-01},

journal = {Annual Review of CyberTherapy and Telemedicine},

volume = {22},

pages = {28–33},

abstract = {Increasingly realistic virtual environments incorporating virtual characters have been used to train or assess actual behavior, such as of people at risk, and identify reasons to remediate or intervene. Technology has improved so rapidly that today’s capabilities to create situations to focus training and intervention outshine past efforts. To name just a few current examples, tools like Unreal’s MetaHuman Creator for creating characters, Midjourney for creating environments, OpenAI’s ChatGPT for scripting, and GIFT for tutoring have enormous potential, as these tools promise to reduce simulation costs and increase realism. This paper, in contrast, discusses some movement in the other direction: Recent efforts suggest that increased realism may not always have resulting cost-benefit for training and assessment. Lessons learned and recommendations are presented to guide future developers. © 2024, Interactive Media Institute. All rights reserved.},

keywords = {Article, Artificial intelligence, character and application fidelity, ChatGPT, Consequential conversations, conversation, Engagement, human, Large language model, Learning, responsibility, responsive virtual humans, social competence, telehealth, Virtual Reality},

pubstate = {published},

tppubtype = {article}

}

@article{marquez_perspective_2023,

title = {A perspective on the synergistic potential of artificial intelligence and product-based learning strategies in biobased materials education},

author = {R. Marquez and N. Barrios and R. E. Vera and M. E. Mendez and L. Tolosa and F. Zambrano and Y. Li},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85162078243&doi=10.1016%2fj.ece.2023.05.005&partnerID=40&md5=76cd274af795123f1e31e345dd36eded},

doi = {10.1016/j.ece.2023.05.005},

issn = {17497728 (ISSN)},

year  = {2023},

date = {2023-01-01},

journal = {Education for Chemical Engineers},

volume = {44},

pages = {164–180},

abstract = {The integration of product-based learning strategies in Materials in Chemical Engineering education is crucial for students to gain the skills and competencies required to thrive in the emerging circular bioeconomy. Traditional materials engineering education has often relied on a transmission teaching approach, in which students are expected to passively receive information from instructors. However, this approach has shown to be inadequate under the current circumstances, in which information is readily available and innovative tools such as artificial intelligence and virtual reality environments are becoming widespread (e.g., metaverse). Instead, we consider that a critical goal of education should be to develop aptitudes and abilities that enable students to generate solutions and products that address societal demands. In this work, we propose innovative strategies, such as product-based learning methods and GPT (Generative Pre-trained Transformer) artificial intelligence text generation models, to modify the focus of a Materials in Chemical Engineering course from non-sustainable materials to sustainable ones, aiming to address the critical challenges of our society. This approach aims to achieve two objectives: first to enable students to actively engage with raw materials and solve real-world challenges, and second, to foster creativity and entrepreneurship skills by providing them with the necessary tools to conduct brainstorming sessions and develop procedures following scientific methods. The incorporation of circular bioeconomy concepts, such as renewable resources, waste reduction, and resource efficiency into the curriculum provides a framework for students to understand the environmental, social, and economic implications in Chemical Engineering. It also allows them to make informed decisions within the circular bioeconomy framework, benefiting society by promoting the development and adoption of sustainable technologies and practices. © 2023 Institution of Chemical Engineers},

keywords = {Artificial intelligence, Bio-based, Bio-based materials, Biobased, ChatGPT, Chemical engineering, Chemical engineering education, Education computing, Engineering education, Formulation, Generative AI, Learning strategy, Learning systems, Material engineering, Materials, Students, Sustainable development, Teaching approaches, Traditional materials, Virtual Reality},

pubstate = {published},

tppubtype = {article}

}