JELAI: Integrating AI and Learning Analytics in Jupyter Notebooks

2025-05-23

AI Summary

Existing educational AI tools lack pedagogical grounding and contextual awareness, and hinder reproducible interactive research in authentic learning environments. This project introduces JELAI—the first open-source platform that deeply integrates fine-grained learning analytics (LA) with context-aware large language model (LLM) tutoring directly within Jupyter Notebook. Its modular, containerized architecture enables joint LA–LLM modeling, real-time multimodal teaching data collection, and AI-driven adaptive scaffolding generation. Built-in telemetry extensions, dynamic prompt augmentation, and middleware ensure low-latency operation and experimental reproducibility. JELAI bridges a critical gap in the researchability of educational AI within authentic programming learning contexts. Empirical validation demonstrates its capabilities in multimodal log analysis, help-seeking pattern recognition, and controlled A/B experiments comparing pedagogical strategies.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Language Grounding & Multi-modal NLP
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Generative AI offers potential for educational support, but often lacks pedagogical grounding and awareness of the student's learning context. Furthermore, researching student interactions with these tools within authentic learning environments remains challenging. To address this, we present JELAI, an open-source platform architecture designed to integrate fine-grained Learning Analytics (LA) with Large Language Model (LLM)-based tutoring directly within a Jupyter Notebook environment. JELAI employs a modular, containerized design featuring JupyterLab extensions for telemetry and chat, alongside a central middleware handling LA processing and context-aware LLM prompt enrichment. This architecture enables the capture of integrated code interaction and chat data, facilitating real-time, context-sensitive AI scaffolding and research into student behaviour. We describe the system's design, implementation, and demonstrate its feasibility through system performance benchmarks and two proof-of-concept use cases illustrating its capabilities for logging multi-modal data, analysing help-seeking patterns, and supporting A/B testing of AI configurations. JELAI's primary contribution is its technical framework, providing a flexible tool for researchers and educators to develop, deploy, and study LA-informed AI tutoring within the widely used Jupyter ecosystem.

Problem

• Integrating AI tutoring with learning analytics in Jupyter Notebooks
• Lack of pedagogical grounding in current AI educational tools
• Challenges in researching student-AI interactions in real learning environments

Innovation

• Integrates Learning Analytics with LLM tutoring
• Modular containerized JupyterLab extension design
• Enables real-time context-aware AI scaffolding