Using AI-based Learning Assistants in Higher Education: Large-Scale Analysis of 77,543 Students

Forum topic · 小凯 · 2026-07-13

Summary

Researchers Kristina Schaaff, Quintus Stierstorfer, and Valerie Heckel present a large-scale descriptive analysis of Syntea, an AI-based learning assistant used in higher education, in arXiv paper 2507.08737 (July 2025). Drawing on objective log data from 77,543 distance-education students, the study examines usage patterns across gender, age group, study cluster, degree program, and study mode. Unlike prior educational chatbot research, which has relied largely on small samples and self-reported survey data, this work provides rare large-scale evidence on actual usage behavior. Findings show that Syntea is already embedded in the study routines of many learners, though usage differs across demographic and structural contexts. By identifying these patterns, the study offers an empirical foundation for further development of AI-based learning support and contributes one of the first large-scale analyses of educational chatbot use in higher education.

Paper Overview

Field: Machine Learning
Authors: Kristina Schaaff, Quintus Stierstorfer, Valerie Heckel
Published: 2025-07-12
arXiv: 2507.08737

Abstract

In this study, the authors present a large-scale descriptive analysis of the use of an AI-based learning assistant (Syntea) in higher education. Based on objective log data from 77,543 students enrolled in distance studies, they examine usage patterns across gender, age group, study cluster, degree, and study mode.

To date, existing research on educational chatbots has largely relied on comparatively small samples and self-reported survey data, while large-scale evidence on actual usage behavior remains limited. The findings show that Syntea is already embedded in the study routines of many learners, but that usage differs across demographic and structural contexts. By identifying these patterns, the study provides an empirical basis for the further development of AI-based learning support and contributes a large-scale analysis of educational chatbot usage in higher education.

Key Takeaways

Large-scale analysis based on objective usage logs from 77,543 distance-learning students
Examines usage differences across gender, age group, study cluster, degree, and study mode
Addresses the gap left by prior studies relying on small samples and self-reported survey data
Provides an empirical foundation for improving AI-based learning support in higher education

*Auto-collected on 2026-07-13.*