Search and Filter

From Textbook To Talkbot: A Case Study Of A Greek-Language Rag-Based Chatbot In Higher Education

Date

AI Overview

Why it matters

The rich morphology and syntactic complexity of the Greek language complicate text segmentation in AI systems, creating a need for tailored retrieval-augmented approaches that support learning without hallucinations.

Study at a glance
  • Question: Which text chunking methods and retrieval depths optimize Greek-language educational chatbot accuracy, completeness, and clarity?
  • Setting and data: Greek university course materials from Family Psychology and Sports Medicine; evaluated using five expert questions per subject.
  • Method: Model evaluation comparing six text chunking strategies and two retrieval depths using expert ratings on a five-point scale.
  • AI tools: Gemini Flash 2.0, dimitriz/st-greek-media-bert-base-uncased
Key findings
  • In Family Psychology, sentence-based paragraph chunking achieved the highest overall score of 4.13 out of 5 across all criteria.
  • In the denser Sports Medicine corpus, preserving original paragraphs combined with deeper retrieval of 50 chunks achieved the highest score of 4.00.
  • Content accuracy was the strongest dimension for most models in Family Psychology, whereas clarity was consistently the highest-scoring dimension in Sports Medicine.

Summary drafted with AI from the full paper and may contain errors. See the full paper for details.

The integration of AI chatbots into educational settings has opened new pathways for transforming teaching and learning, offering enhanced support to both educators and learners. This study investigates the design and application of an AI chatbot as an educational tool in higher education. Designed to operate in the Greek language, the chatbot addresses linguistic challenges unique to Greek while delivering accurate, context grounded support aligned with the curriculum. The AI chatbot is built on the Retrieval Augmented Generation (RAG) framework by grounding its responses in specific course content. RAG architecture significantly enhances the chatbots reliability by providing accurate, context-aware responses while mitigating common challenges associated with large language models (LLMs), such as hallucinations and misinformation. The AI chatbot serves a dual purpose: it enables students to access accurate, ondemand academic support and assists educators in the rapid creation of relevant educational materials. This dual functionality promotes learner autonomy and streamlines the instructional design process. The study aims to evaluate the effectiveness, reliability, and perceived usability of RAG based chatbots in higher education, exploring their potential to enhance educational practices and outcomes as well as supporting the broader adoption of AI technologies in language specific educational contexts. Findings from this research are expected to contribute to the emerging field of AI driven education by demonstrating how intelligent systems can be effectively aligned with pedagogical goals.