Schlagwort: chatbot

Veröffentlicht am

[publication] Generative AI Chatbots in Secondary Mathematics Education: Development and Implementation of a Dynamic Large Language Model-Based Learning Assistant for Quadrilaterals #tugraz

Our contribution titled „Generative AI Chatbots in Secondary Mathematics Education: Development and Implementation of a Dynamic Large Language Model-Based Learning Assistant for Quadrilaterals“ is now published.

Abstract:
As artificial intelligence becomes more and more a part of education, the challenge is not about having access to generative tools, but about connecting them with the goals of the curriculum and the needs of the classroom. This chapter presents the design and evaluation of a large language model–based chatbot developed specifically for teaching quadrilaterals in lower secondary mathematics. The chatbot integrates fine-tuning with retrieval-augmented generation (RAG), combining accurate, curriculum-aligned content with flexible, conversational support. The chatbot allows learners to ask conceptual questions, solve problems step by step, receive guided hints, and generate flashcards or exercises of varying difficulty. A hybrid routing mechanism selects the most appropriate response strategy based on user intent. Evaluations using both isolated prompts and multi-turn dialogues demonstrate that the hybrid system significantly outperforms standard LLM baselines in terms of accuracy, consistency, and pedagogical suitability. A classroom trial with 20 students confirmed the tool’s usability and effectiveness; students reported high satisfaction and meaningful engagement. This study demonstrates that, with careful content and architectural structuring, generative AI can enhance student learning while supporting differentiated instruction. Future directions include scaling the approach to other topics and incorporating multimodal capabilities.

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

Reference: Mallweger, M., Brünner, B., Ebner, M. (2026). Generative AI Chatbots in Secondary Mathematics Education: Development and Implementation of a Dynamic Large Language Model-Based Learning Assistant for Quadrilaterals. In: Auer, M.E., Nikou, S.A. (eds) GenAI in Novel Educational Applications. Studies in Computational Intelligence, vol 1260. Springer, Cham. https://doi.org/10.1007/978-3-032-16153-6_7

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

Veröffentlicht am

[publiation] AI-Powered Chatbots for Education Using RAGs #tugraz

Our publication about „AI-Powered Chatbots for Education Using RAGs“ got published right now.

Abstract:
This study examines the use of Retrieval-Augmented Generation (RAG) in AI-powered educational chatbots, focusing on embedding efficiency, large language model (LLM) performance, and context integrity. Implemented within the MOOC Informatik-Fit at TU Graz, the system supports scalable, curriculum-aligned self-paced learning. Three embedding models were evaluated, with text-embedding-ada-002 offering the best balance between semantic quality and cost-efficiency. Subsequently, three LLMs—GPT-3.5 Turbo, GPT-4o, and GPT-4o mini—were compared, revealing GPT-4o mini as the most cost-effective option while maintaining high accuracy and contextual coherence. Ethical robustness was assessed using 30 adversarial prompts, demonstrating strong resistance to jailbreaking in both GPT-4o and GPT-4o mini, supporting their suitability for secure and pedagogically reliable MOOC applications.
The paper also presents a replicable framework for the implementation of RAG-based systems, with the objective of promoting personalized, ethical, and accessible digital education on a large scale.

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

Reference: Brünner, B., Deutschmann, F., Etzelstorfer, S., Lechner, A., Schön, S. & Ebner, M. (2029) “AI-Powered Chatbots for Education using RAGs: A Study on Embedding Efficiency, LLM Performance, and Context Integrity”. In: Transforming Education with Singularity Technologies: Lifelong Learning from Childhood to Adulthood (1st ed.). Uğur, S. (Ed.) Chapman and Hall/CRC. Chapter 9. 21 pages https://doi.org/10.1201/9781003584339

Veröffentlicht am

[presentation] OER as the basis for an AI chatbot, using iMooX.at as an example #tugraz

I did a talk about „OER as the basis for an AI chatbot, using iMooX.at as an example“ for the Open Education Week @ National eLearning Center in Saudi-Arabia:

Talk for the Open Education Week at National eLearning Center, Riyadh, Saudi Arabia, titled „From Open Content to Personalized Pathways: OER and AI for Lifelong Learning“.
The aim of the online workshop is listed as „to explore how open education and OER, enhanced by AI and digital learning ecosystems, can move beyond static content access toward scalable, personalized, and responsible lifelong learning—while ensuring quality, trust, transparency, and openness in an AI-driven era.“
In this talk, I introduce the use of Open Educational Resources for an AI-based Chatbot within a Massive Open Online Course on the platform iMooX.at

[Link to the slides]

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

Veröffentlicht am

[publication] Exploring genAI Chatbots in MOOCs: Analyzing Student Interactions and Self-Regulated Learning Behaviors #imoox #tugraz #research

Our publication about „Exploring genAI Chatbots in MOOCs: Analyzing Student Interactions and Self-Regulated Learning Behaviors“ got published.

Abstract:
The integration of generative AI (genAI) chatbots into Massive Open Online Courses (MOOCs) presents new opportunities for supporting self-regulated learning (SRL). This study examines 1,302 chat-bot interactions from two Austrian blended MOOCs, where a retrieval-augmented generation (RAG) chatbot based on GPT 4o-mini was deployed to assist students. Using the process-action framework by Lai (2024), we categorize chatbot interactions into key SRL processes: defining , seeking, engaging, and reflecting. Results show that students predominantly use the chatbot for information retrieval, content summarization, and quiz-based reinforcement, with 41% of interactions classified as information search queries and 17% as rehearsal. However, engagement with metacognitive SRL strategies, such as goal setting and self-evaluation, remains low. Additionally, non-learning interactions, including humor-driven conversations, functional queries, and prompt injection attempts, showcase ways students interact with AI in educational settings. Based on our findings, we propose refinements to the existing SRL process-action framework, incorporating new categories to better account for genAI chatbot-specific interactions, such as Evaluation of Information Quality and Reformatting. We discuss implications for chat-bot integration in MOOCs, emphasizing AI-generated quizzes, structured feedback, and safeguards against misuse.

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

Rerence: Brünner, B., Ebner, M., Schön, S. (2025). Exploring GenAI Chatbots in MOOCs: Analyzing Student Interactions and Self-regulated Learning Behaviors. In: Hamonic, E., Sharrock, R. (eds) Digital Education: Shaping Sustainable Lifelong Learning for All in the Era of AI. EMOOCS 2025. Lecture Notes in Computer Science, vol 15733. Springer, Cham. https://doi.org/10.1007/978-3-032-00056-9_2

This is an impactful contributions, methodological rigor, and exceptional novelty in the research field of AI in education using a Chatbot within a MOOC-platform (iMooX.at)

Veröffentlicht am

[mooc] Informatik-FIT #tugraz #brückenkurs

Fast schon traditionell, darf ich den Start des MOOC „Informatik-FIT“ verkünden, welcher vor allem unseren Studienanfänger:innen helfen soll, den Einstieg in die Informatik zu erleichtern:

Die Vielfalt der Probleme, die in der Informatik behandelt werden, macht eine kurze und dennoch vollständige Definition dessen, was Informatik ist, unmöglich.
Unmöglich ist es auch, alle Themen in einem Einführungskurs unterzubringen.
Irgendwo müssen wir aber trotzdem anfangen und so haben wir versucht, die wichtigsten Grundbegriffe und Ideen der Informatik auszuwählen und diese so zu vermitteln, dass sich die Teilnehmer:innen schnell ein breiteres Bild von der Informatik machen können.
Darüber hinaus soll es für die Teilnehmer:innen möglich sein, Zusammenhänge zwischen den einzelnen Themen zu erkennen bzw. herzustellen. 

Der Trailer zum MOOC:

YouTube

Mit dem Laden des Videos akzeptieren Sie die Datenschutzerklärung von YouTube.
Mehr erfahren

Video laden

Die Teilnahme ist natürlich wie immer kostenfrei: [Link zur Anmeldung zum MOOC]

Hinweis: Letztes Jahr hatten wir erstmals einen KI-basierten Chatbot im Einsatz, heuer darf ich verraten ist es eine Videochatbot. Wir sind gespannt wie gut dieser das Lernen unterstützen kann.

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

[publication] Chatbots in Education: A Systematic Rapid Literature Review #AIinEdu #tugraz #research

Our contribution to this year’s SITE conference in Orlando titled „Chatbots in Education: A Systematic Rapid Literature Review“ is published.

Abstract:
This review explores the role of chatbots in education through a detailed literature review of 60 records. As chatbots become increasingly embedded in students‘ daily lives, their presence in primary, secondary, and tertiary education is expanding rapidly. By analyzing the selected papers, this review highlights both the opportunities and challenges faced by educators and students when using chatbots. The findings indicate that the integration of AI in education offers significant potential but requires careful consideration. In particular, the study emphasizes the need for improved teacher and student training, updated policies, and effective assessments to maintain academic integrity and enhance learning outcomes.

[publication @ ResearchGate]

Reference: Gregorac, A., Brünner, B. & Ebner, M. (2025). Chatbots in Education: A Systematic Rapid Literature Review. In Proceedings of SITE 2025 (pp. 588-593). Waynesville, NC USA: Association for the Advancement of Computing in Education (AACE). Retrieved March 24, 2025 from https://www.learntechlib.org/primary/p/225579/.