A terinformatika allasa 2026-ban — AI-powered interactive learning platform for geoinformatics

Read full text Summarise with VIRAT
Authors: Zsolt Zoltán Fehér
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

An AI-powered interactive learning platform for a 24-chapter Hungarian university geoinformatics textbook. The platform provides a full book reader with markdown rendering, LaTeX equations, and embedded illustrations; a multi-provider LLM chat with Retrieval-Augmented Generation (RAG) over the textbook content; a self-assessment quiz system with 7,339 pre-generated questions (MCQ, true/false, fill-in-the-blank) and SM-2 spaced repetition flashcards; an interactive concept dependency graph; AI-generated chapter summaries; full-text search across all chapters; cross-chapter clickable references; PDF export of quiz results; and a per-user LLM provider configuration panel supporting OpenAI, Google Gemini, Anthropic Claude, Ollama, LM Studio, and Groq. IMPORTANT: Both the textbook content and the majority of the application code were generated using large language models (LLMs). This material should be considered AI-generated and has not been independently peer-reviewed. It is intended as an educational technology demonstration and research artifact, not as an authoritative geoinformatics reference. Technology stack: FastAPI (Python), React + Vite + TailwindCSS, ChromaDB, sentence-transformers, KaTeX, remark-gfm.

Fields of Study & Subjects

Artificial Intelligence in Education Intelligent Tutoring Systems and Adaptive Learning Educational Technology and E-Learning

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
20 March 2026
Language
EN