Predictive framework for student engagement and performance in gamified learning environments
2025-2026 PIBIC project focused on creating a predictive framework for student engagement and performance in gamified learning environments by combining Octalysis, neuroscientific indicators, learning analytics, and machine learning.
Overview
Ongoing project. Reported period: PIBIC 2025-2026.
This project investigates the construction of a predictive framework for student engagement and performance in gamified learning environments. The proposal combines Octalysis principles, learning-related neuroscientific indicators, learning analytics, and machine learning models to support earlier, more personalized, evidence-based pedagogical decisions.
The project builds on concrete gamification experiences in undergraduate courses, including the Feudal Dawn experience, and organizes their data into diagnostic instruments, indicators, and models that support the personalization of teaching strategies.
General data
| Field | Information |
|---|---|
| Nature | Research, development, and innovation in educational gamification, learning analytics, and artificial intelligence applied to education |
| Status | Ongoing |
| Start year | 2025 |
| End year | 2026 |
| Program | PIBIC 2025-2026 |
| Coordination | Prof. Sergio Antonio Andrade de Freitas |
| Institution involved | University of Brasilia |
| Executing institution | University of Brasilia |
| Unit | Faculty of Sciences and Technologies in Engineering |
| Research institution-company cooperation | Not informed in the project record |
| Innovation potential | Framework, diagnostic instruments, indicators, and predictive models for personalizing gamified learning environments |
Objectives
The main objectives are to:
- structure a framework to predict student engagement and performance in gamified learning environments;
- combine Octalysis motivational dimensions with learning, engagement, and performance indicators;
- explore machine learning models to support predictions and pedagogical recommendations;
- consolidate diagnostic instruments applicable at the start of a semester; and
- support the evolution of the EduTrack and EduTrack AI products.
Team
| Participant | Role |
|---|---|
| Sergio Antonio Andrade de Freitas | Coordinator and undergraduate research advisor |
| Cristiane Soares Ramos | Researcher |
| Daniel Rodrigues da Rocha | Undergraduate research student advised by Prof. Sergio |
| Davi Rodrigues da Rocha | Undergraduate research student advised by Prof. Sergio |
| Mylena Angélica Silva Farias | Undergraduate research student advised by Prof. Sergio |
Related products
Linked C&T production
| Year | Output | Type | Note |
|---|---|---|---|
| 2026 | A Motivation-Aware Diagnostic Instrument for Personalized and Gamified Computing Education | Conference paper | Result derived from the Feudal Dawn experience and linked to the 2025-2026 PIBIC project |
Linked supervision
| Year | Supervision | Type |
|---|---|---|
| 2025 | Predictive Framework for Student Engagement and Performance in Gamified Learning Environments Based on Octalysis, Neuroscientific Indicators, and Machine Learning | Undergraduate research - Daniel Rodrigues da Rocha |
| 2025 | Predictive Framework for Student Engagement and Performance in Gamified Learning Environments Based on Octalysis, Neuroscientific Indicators, and Machine Learning | Undergraduate research - Davi Rodrigues da Rocha |
| 2025 | Predictive Framework for Student Engagement and Performance in Gamified Learning Environments Based on Octalysis, Neuroscientific Indicators, and Machine Learning | Undergraduate research - Mylena Angélica Silva Farias |