- Updated: August 26, 2026
- 2 min read
RIACT: A Responsible AI System for Personalized Study Habit Tracking and Early Burnout Signal Detection in University Students
RIACT: A Responsible AI System for Personalized Study Habit Tracking and Early Burnout Signal Detection in University Students
Student burnout is a growing crisis in higher education, with prevalence rates ranging from 12% to over 70%. Traditional productivity tools merely record activity without providing insight, leaving students unaware of harmful study patterns until academic performance declines. RIACT (Record, Insight, Analyze, Coach, Track) addresses this gap by offering a web‑based, responsible AI platform that logs structured study sessions, computes net focus time, and surfaces early burnout signals through transparent, rule‑based analytics and a constrained large‑language‑model (LLM) for personalized recommendations.
Key Features
- Structured Session Logging: Users record study sessions by location, start/end time, and break periods.
- Net Focus Time Calculation: Breaks are automatically deducted to provide a realistic measure of productive study time.
- Deterministic Burnout Detection: Week‑over‑week behavioural comparisons trigger alerts based on auditable rules, ensuring explainability.
- LLM‑Enhanced Coaching: A constrained LLM generates contextualized, observation‑based recommendations without making medical diagnoses.
- Responsible AI Principles: All warnings are rule‑driven, outputs are framed as observations, and data collection is limited to self‑reported fields.
Why RIACT Matters
The system empowers students with real‑time visibility into their study habits, enabling proactive adjustments before burnout manifests. By integrating explainable AI with responsible design, RIACT bridges the gap between raw activity data and actionable insights, aligning with emerging standards for ethical AI in education.
Evaluation Framework
RIACT’s burnout signals are validated against established instruments such as the Maslach Burnout Inventory (MBI) and the Student‑Perceived Stress Scale (SPSS). Ongoing user studies on the UBOS platform will assess predictive accuracy, user satisfaction, and longitudinal impact on academic outcomes.
Get Started
University students and administrators can explore RIACT by visiting the RIACT demo page. For developers interested in the underlying architecture, detailed documentation is available on our developer portal.
Stay tuned for future updates and research publications on the UBOS blog.
Andrii Bidochko
CTO UBOS
Andrii Bidochko is an AI entrepreneur and researcher focused on AI agents, reinforcement learning, and autonomous systems. He writes about the technologies shaping the future of machine intelligence, from frontier models and agent architectures to real-world AI applications.