Schlagwort: hcii

Veröffentlicht am

[publication] Craft and Technology Education in a Rural Area: Insights from the First Year of “Technik Für Kinder Vulkanland” #tugraz #education

Our publication titled „Craft and Technology Education in a Rural Area: Insights from the First Year of “Technik Für Kinder Vulkanland” has been published.

Abstract:
This study examines the first year of Technik für Kinder Vulkanland (TfKV), a rural makerspace initiative in South-Eastern Austria, through an exploratory mixed-methods evaluation focusing on parents’ and mentors’ perspectives. The initiative is designed as a weekly club format for children and adolescents aged 7 to 14, complemented by holiday workshops. The evaluation addresses five research questions covering pre-participation expectations and feasibility of the weekly club format (RQ1), pilot experiences after one month of regular attendance (RQ2), medium-term participation experiences after six months (RQ3), holiday workshop formats (RQ4), and reflective perspectives from one mentor and the lead mentor (RQ5). The results show that rural distance is not universally experienced as a barrier; structured weekly continuity is perceived as stabilizing; mentoring quality and intergenerational interaction are central to perceived success; and participation is associated with process-oriented learning, perseverance, and growing confidence in dealing with mistakes, exceeding the primarily motivational effects of episodic exposure formats. At the same time, mentor reflections reveal pedagogical tensions regarding scaffolding practices and instructional orientation, particularly between tool-centered skill development and project-centered meaning-making. Taken together, the findings suggest that the TfKV club format is perceived not merely as a recreational workshop but as a potential regional hub for craft and technology education. The study provides first insights into the viability and developmental dynamics of a community-embedded rural makerspace model that integrates continuity and mentoring structures.

[full paper @ publisher’s homepage]
[draft @ ResearchGate]

Reference: Wolf, D., Ebner, M., Miklós, J. (2026). Craft and Technology Education in a Rural Area: Insights from the First Year of “Technik Für Kinder Vulkanland”. In: Smith, B.K., Borge, M. (eds) Learning and Collaboration Technologies. HCII 2026. Lecture Notes in Computer Science, vol 16731. Springer, Cham. https://doi.org/10.1007/978-3-032-30542-8_22

Veröffentlicht am

[publication] Development and Evaluation of an AI-Supported Teacher Assistant Tool (AI-TAT) to Foster Self-Regulated Learning #tugraz #AIinEducationa

Our publication titled „Development and Evaluation of an AI-Supported Teacher Assistant Tool (AI-TAT) to Foster Self-Regulated Learning“ has been published.

Abstract:
Self-regulated learning (SRL) is increasingly recognised as a key competence for students, yet many teachers struggle to integrate SRL concepts into concrete classroom materials like worksheets. In this paper, SRLly is presented, an AI-supported teacher assistance tool (AI-TAT) that helps teachers revise existing worksheets to better scaffold SRL processes. Rather than submitting entire documents to a large language model (LLM), SRLly performs local preprocessing of uploaded PDFs to extract text with positional metadata, segments the worksheet into meaningful blocks, and sends only relevant blocks for analysis. Based on this structured representation, the system generates actionable recommendations aligned with four SRL dimensions (planning, strategy, monitoring, reflection). Recommendations are presented in an easy-to-use interface that supports teachers’ workflows by providing short rationales and concrete recommendations with ready-to-use text snippets that can be copied. We conducted an initial evaluation during a teacher professional development training with 30 teachers at an Austrian school (student age range 10–18). Overall perceptions were positive: 76% of participants rated SRLly as good or very good. Likert-scale results indicated high perceived usefulness and feasibility, while trustworthiness ratings were more mixed, highlighting reliability of AI output as a key area for improvement. Our findings suggest that structured, material-centred AI feedback can support teachers in integrating SRL into everyday worksheet design, while underscoring the need for stronger reliability and real-world validation.

[full article @ publisher’s homepage]
[draft @ ResearchGate]

Reference: Geier, G., Ebner, M., Burgsteiner, H. (2026). Development and Evaluation of an AI-Supported Teacher Assistant Tool (AI-TAT) to Foster Self-Regulated Learning. In: Smith, B.K., Borge, M. (eds) Learning and Collaboration Technologies. HCII 2026. Lecture Notes in Computer Science, vol 16733. Springer, Cham. https://doi.org/10.1007/978-3-032-30784-2_12

Veröffentlicht am

[publication] On Using an LLM-Based Approach for Automatic Evaluation of Programming Tasks in MOOC Videos #tugraz #AIinEducation

Our publication about „On Using an LLM-Based Approach for Automatic Evaluation of Programming Tasks in MOOC Videos“ has been published.

Abstract:
Interactive videos promote learner engagement by transforming the passive activity of watching videos into an active learning process. LIVE, a web platform developed in previous research that allows for the integration of interactive elements into videos, also supports embedding programming tasks. However, at the beginning of our research, the output of the submitted solution was automatically compared to the reference output, but the code itself still had to be checked manually, as no automatic process was available to verify the solution and provide feedback. To address this, a stand-alone application was developed that automatically evaluates students’ solutions to Python programming tasks using a self-hosted large language model. This application was then integrated into the existing platform. To test this approach, a massive open online course containing four interactive videos with several programming tasks and quizzes was created. Students’ performance was analyzed using quiz results, task submissions, self-assessments, and user statistics provided by the course platform and LIVE. The results indicate that utilizing a large language model for automated feedback can positively impact learning outcomes. However, some limitations must be taken into account, such as the need to correct some of the model’s generated outputs manually due to insufficient feedback quality for certain tasks. This suggests that the combination of automated and manual evaluation seems to be the most effective approach for now.

[full article @ publisher’s homepage]
[draft @ ResearchGate]

Reference: Kindlhofer, C., Wachtler, J., Ebner, M. (2026). On Using an LLM-Based Approach for Automatic Evaluation of Programming Tasks in MOOC Videos. In: Smith, B.K., Borge, M. (eds) Learning and Collaboration Technologies. HCII 2026. Lecture Notes in Computer Science, vol 16733. Springer, Cham. https://doi.org/10.1007/978-3-032-30784-2_13

Veröffentlicht am

[publication] How Embodiment Changes AI Tutoring: Comparing Student Perceptions of Text and AI Human Avatar-Based Chatbot Systems #AIinEducation #chatbot #tugraz

Our publication titled „How Embodiment Changes AI Tutoring: Comparing Student Perceptions of Text and AI Human Avatar-Based Chatbot Systems“ is now published.

Abstract:
Embodied conversational interfaces are able to deliver generative AI tutoring via synthesised speech and human-like video avatars. However, there is limited empirical evidence on how embodiment shapes the learner experience and self-regulated learning (SRL). This study compares the perceptions of students interacting with a text-based Retrieval-Augmented Generation (RAG) tutor and an avatar-based RAG tutor in two authentic higher education contexts (introductory computer science and Python programming) across two European universities. Adopting a Design-Based Research approach, we collected (1) questionnaire data from users and non-users, and (2) anonymised interaction logs comprising 341 user messages, which were coded using an SRL process–action framework. The results show that the perceived level of learning support is largely consistent with previous text-only deployments: the tutor is primarily valued for providing explanations and support related to practice, while motivational support is still comparatively weak. However, embodiment notably improves perceptions of the system as a communication partner, with active users rating this dimension more positively than non-users. Modality ratings suggest that audio output is perceived as more helpful than the visual avatar. Log analyses show that interactions are still dominated by information-seeking (Seeking–Search) and that metacognitive SRL actions (e.g. goal setting and self-evaluation) are rare. Embodiment also introduces additional peripheral interactions (e.g. character-focused prompts and human-likeness checks), thereby increasing the proportion of non-learning dialogue. Overall, the findings suggest that, while embodiment enhances social presence, it does not automatically foster deeper SRL. Explicit pedagogical scaffolding is needed to encourage learners to engage in metacognitive regulation.

[full paper @ publisher’s homepage]
[draft @ ResearchGate]

Reference: Brünner, B., Nestler, M., Pucher, L., Ebner, M. (2026). How Embodiment Changes AI Tutoring: Comparing Student Perceptions of Text and AI Human Avatar-Based Chatbot Systems. In: Smith, B.K., Borge, M. (eds) Learning and Collaboration Technologies. HCII 2026. Lecture Notes in Computer Science, vol 16731. Springer, Cham. https://doi.org/10.1007/978-3-032-30542-8_25

This is an impactful contributions, methodological rigor, and exceptional novelty in the research field of AI in education, Chatbots and MOOCs.

Veröffentlicht am

[publication] Empowering Self-Regulated Learning Through Technology and the Teacher’s Role – A Systematic Literature Review #research

This is an impactful contributions, methodological rigor, and exceptional novelty in the research field of AI in education and Self-Regulated Learning.

Our research work titled „Empowering Self-Regulated Learning Through Technology and the Teacher’s Role – A Systematic Literature Review“ is published.

Abstract:
Self-regulated learning (SRL) has been demonstrated in numerous scientific studies as an effective alternative to traditional teaching methods, fostering individual learning processes. The added value of educational technology in supporting SRL has also been widely researched and largely validated. Within this context, the teacher plays a pivotal role. However, much of the existing research has been conducted at universities , while the secondary education level has received comparatively less attention. To gain an overview of the teacher’s influence on students‘ SRL processes, a PRISMA based systematic literature review was conducted. From an initial pool of 553 documents, 27 relevant studies were identified and analyzed. The selected studies were examined to collect data addressing the research questions, focusing on identifying effective teaching methods and essential teacher competencies for fostering SRL in technology-enhanced classrooms. Furthermore, the analysis highlights the evolving role of teachers and underscores the need for additional training to support these changes.

[full article @ publisher’s website]
[draft @ researchgate]

Reference: Geier, G., Ebner, M., Burgsteiner, H. (2025). Empowering Self-Regulated Learning Through Technology and the Teacher’s Role – A Systematic Literature Review. In: Smith, B.K., Borge, M. (eds) Learning and Collaboration Technologies. HCII 2025. Lecture Notes in Computer Science, vol 15807. Springer, Cham. https://doi.org/10.1007/978-3-031-93567-1_5

Veröffentlicht am

[publication] Synthetic Educators: Analyzing AI-Driven Avatars in Digital Learning Environments #AIinEducation #tugraz

This is an impactful contributions, methodological rigor, and exceptional novelty in the research field of AI in education.

Our publication „Synthetic Educators: Analyzing AI-Driven Avatars in Digital Learning Environments“ at this year’s HCII conference is published.

Abstract:
Videos can be used in a variety of ways in learning environments today. With advances in generative AI technologies, tools such as HeyGen and ElevenLabs make it easy to create synthetic teachers, promising efficiency and accessibility. This study investigates the impact of AI-generated teaching video avatars on learners‘ emotional responses. A mixed-method approach was adopted, in which 55 participants were shown AI-generated videos and videos with real instructors. Emotional engagement was measured using FaceReader Online, along with quiz questions and follow-up interviews to gauge knowledge retention and perceptions of this educational technology. Results indicate that AI avatars effectively convey content and weakly elicit better recall rates and positive emotional responses comparable to those of real instructors. However, concerns were raised about emotional authenticity and engagement, highlighting the need for improved avatar design. The study concludes with a discussion of the potential and limitations of AI avatars and argues for their thoughtful integration to improve educational equity and learning outcomes.

[full article @ publisher’s homepage]
[draft @ researchgate]

Reference: Struger, P., Brünner, B., Ebner, M. (2025). Synthetic Educators: Analyzing AI-Driven Avatars in Digital Learning Environments. In: Smith, B.K., Borge, M. (eds) Learning and Collaboration Technologies. HCII 2025. Lecture Notes in Computer Science, vol 15807. Springer, Cham. https://doi.org/10.1007/978-3-031-93567-1_13

Veröffentlicht am

[publication] InfoFit and Beyond: AI Chatbots as EdTech Tools for Self-Regulated Learning in MOOCs #AIinEducation #research

This is an impactful contributions, methodological rigor, and exceptional novelty in the research field of AI in education.

Our publication titled „InfoFit and Beyond: AI Chatbots as EdTech Tools for Self-Regulated Learning in MOOCs“ at this year’s HCII conference is available.

Abstract:
Massive Open Online Courses (MOOCs) have become essential for the democratization of education by providing accessible learning opportunities to broad audiences. However, their asynchronous and open structure is challenging for learning, especially in terms of maintaining engagement, and self-regulated learning (SRL) is necessary. This study investigates the integration of a retrieval-augmented-generation (RAG) chatbot into a MOOC and uses generative AI (genAI) to enhance learn-ers‘ SRL processes. The chatbot is based on Zimmermann’s SRL framework and is prepared for the MOOC content, basics of computer science. It is designed to support learners in the forethought, performance, and self-reflection phases by providing concise, context-specific responses. A mixed-method evaluation with 79 participants revealed high levels of satisfaction , with over 98% of respondents recommending the chatbot for future courses. The chatbot proved effective in supporting tasks such as summarization and concept clarification; however, its role in maintaining motivation emerged as a key area for further investigation. These findings underscore the transformative potential of AI chatbots in asynchronous learning environments, while also highlighting the importance of incorporating multimodal and motivational features to maximize educational technology (EdTech) impact.

[full article @ publisher’s homepage]
[draft @ ResearchGate]

Reference: Brünner, B., Ebner, M. (2025). InfoFit and Beyond: AI Chatbots as EdTech Tools for Self-Regulated Learning in MOOCs. In: Smith, B.K., Borge, M. (eds) Learning and Collaboration Technologies. HCII 2025. Lecture Notes in Computer Science, vol 15807. Springer, Cham. https://doi.org/10.1007/978-3-031-93567-1_4

Veröffentlicht am

[presentation] Synthetic Educators: Analyzing AI-Driven Avatars in Digital Learning Environments #HCII25

Our research about AI-Driven Avatars was presented at 27th International Conference on Human-Computer Interaction, Gothenburg, Sweden.

Struger, P., Brünner, B., & Ebner, M. (2025, Juni 23). Presentation: Synthetic Educators: Analyzing AI-Driven Avatars in Digital Learning Environments. Graz University of Technology. https://doi.org/10.3217/bngt5-p2053

Veröffentlicht am

[publication] Evaluating the Efficacy of Automated Video Editing in Educational Content Production: A Time Efficiency and Learner Perspective Study #tugraz #research

Out publication „Evaluating the Efficacy of Automated Video Editing in Educational Content Production: A Time Efficiency and Learner Perspective Study“ was published.

Abstract:
Automated editing technology offers notable efficiencies in educational video production. This study contrasts the time-saving benefits of automated editing against manual professional editing. Raw learning video footage was recorded in a professional studio with a green screen and presented in a frontal lecture style. The raw footage underwent editing by both an automated tool and professional editors. Time comparison results revealed significant savings with the use of automated tools. The paper further investigates the impact of automated editing on the learning video quality from the learners’ viewpoint. An online survey with 129 participants evaluated their perceptions of potential learning outcomes after viewing automatically and manually edited versions of two videos. The survey found a statistically significant difference in perceived learning potential from one of the videos, although not for both. Additionally, the study considers how differences in study group characteristics might influence these results. In summary, while automated editing presents a compelling case for production time reduction, its impact on the perceived quality of educational videos remains uncertain, necessitating additional research to understand the subtleties of learner interaction with video content.

[article @ publisher’s homepage]
[draft @ ResearchGate]

Reference: Nußbaumer, D., Mair, B., Schön, S., Edelsbrunner, S., Ebner, M. (2024). Evaluating the Efficacy of Automated Video Editing in Educational Content Production: A Time Efficiency and Learner Perspective Study. In: Zaphiris, P., Ioannou, A. (eds) Learning and Collaboration Technologies. HCII 2024. Lecture Notes in Computer Science, vol 14722. Springer, Cham. https://doi.org/10.1007/978-3-031-61672-3_15

Veröffentlicht am

[publication] Promotion of Emotional Learning in Technical and Social Domains: A Systematic Review #tugraz #research #hcii

Our publication, „Promotion of Emotional Learning in Technical and Social Domains: A Systematic Review, “ was published.

Abstract:
Different learning approaches and new Learning Environment Systems (LES) are evolving rapidly these days and are designed by taking more and more individual skills and personal characteristics and preferences into account. Also Emotional Learning is gaining more importance when it comes to different learning environments in the technical domain as well as in the social context. Emotional Learning can help to support the overall engagement in learning and approaching learning achievements significantly. This paper should give some deeper insights into Emotional Learning, which possibilities exist to support it in a meaningful way and how feedback of emotional states can be obtained in Learning Environment Systems in higher education. For this purpose a literature review was chosen as the underlying research method to explore and find the necessary answers in various scientific articles, encyclopedias and relevant conference papers from different sources. The outcome will show different state-of-the-art approaches and tools to promote Emotional Learning and how to incorporate emotional learning support in Learning Environments.

[article @ publisher’s homepage]
[draft @ ResearchGate]

Reference: Struger, P., Brünner, B., Ebner, M. (2024). Promotion of Emotional Learning in Technical and Social Domains: A Systematic Review. In: Zaphiris, P., Ioannou, A. (eds) Learning and Collaboration Technologies. HCII 2024. Lecture Notes in Computer Science, vol 14723. Springer, Cham. https://doi.org/10.1007/978-3-031-61685-3_18