Projects |

LARA

Mon, 09 Feb 2026 00:00:00 +0000

LARA (Learning Analytics for Reactive Assistance) is a framework for using learning analytics to drive reactive, AI-supported assistance in programming education. It is the basis of the Leia 2.0 pedagogical assistant.

Leia 2.0

Mon, 09 Feb 2026 00:00:00 +0000

Leia 2.0 is an AI-powered pedagogical assistant for programming education, studied with cohorts of engineering students in Colombia.

Konrad Think-Pair-Share

Wed, 01 Jan 2025 00:00:00 +0000

Konrad Think-Pair-Share is a collaborative learning platform I developed at Fundación Universitaria Konrad Lorenz to study how artificial intelligence can be integrated into the Think-Pair-Share (TPS) methodology, and how learning analytics can measure its effect on students’ creative thinking.

The platform

A custom web platform with real-time synchronisation and built-in learning analytics, following the three TPS phases:

Think (8 min): each student reflects and writes individually in a private workspace.
Pair (20 min): anonymous pairs write together in a synchronised editor. In the AI-enhanced version, both students can consult a Google Gemini-powered chatbot, Lupi, instructed to help them reflect on the topic without giving direct answers, by asking questions, suggesting other perspectives and giving feedback on structure and clarity.
Share (15 min): pairs present and discuss their conclusions with the whole class.

The platform logs every writing interaction, the final texts and the full student–chatbot dialogues for analysis.

Teachers create and manage the activities, configure the parameters of each Think-Pair-Share phase and monitor their students’ progress; students are automatically assigned to a room with a partner.

The study

A cluster-randomised quasi-experimental study with 140 Systems Engineering students in seven classes (Programming Fundamentals, Software Analysis and Design, and Software Engineering): 80 students used the AI-enhanced platform and 60 used the same platform without AI. Linguistic creativity was analysed along four dimensions (fluency, flexibility, originality and elaboration) using lexical diversity (TTR, MTLD), topic modelling, productivity metrics and the similarity between students’ texts and the chatbot’s responses.

Findings

The best results came from moderate integration of the AI suggestions (similarity of 0.3–0.7 with the chatbot’s responses), which 70% of participants achieved.
The AI-supported group showed 30–37% productivity gains and a 99% increase in thematic diversity, with moderate lexical standardisation effects.
For practice: include an individual reflection phase before AI-supported writing, design AI support that promotes linguistic diversity while preserving students’ creative autonomy, and avoid relying on length-sensitive metrics such as TTR when assessing creative outcomes.

Read the full article, published open access in the Journal of Learning Analytics: .

COURAGE

Fri, 01 Jan 2021 00:00:00 +0000

COURAGE was a project funded by the Volkswagen Foundation (2019–2023) to build a virtual companion that educates and supports teenage students facing the threats of social media, such as biases, hate speech, bullying and fake news. The Universitat Pompeu Fabra’s TIDE group was one of the project partners.

Within COURAGE I worked on narrative scripts: collaborative learning scripts embedded in a simulated social media platform, which combine game mechanics and counter-narratives to strengthen students’ social media literacy and self-protection skills, and studied their effect on students’ intrinsic motivation and engagement.

PyramidApp

Wed, 01 Jan 2020 00:00:00 +0000

PyramidApp is a tool, developed by the TIDE group at Universitat Pompeu Fabra, for running Pyramid (snowball) collaborative learning flow patterns: students first answer individually and then discuss and agree on answers in progressively larger groups.

During my PhD I studied how game mechanics can foster intrinsic and extrinsic motivation in these scripts: whether they can induce a flow state, how reward-based gamification affects participation, and how group awareness features in PyramidApp influence student engagement and learning outcomes. This work is the core of my doctoral thesis, Motivation-Driven Mechanics in Computer-Supported Collaborative Learning Scripts.

Gamification for Teaching Programming

Tue, 01 Jan 2019 00:00:00 +0000

A funded research project at the Universidad Autónoma de Bucaramanga (UNAB) that developed a methodology to foster learning of computer programming through gamification, together with a mobile application to help students and teachers follow the state of their learning.

The project informed a pedagogical diagnosis and restructuring of the computer programming courses in the Systems Engineering programme.

AnimVR

Wed, 27 Apr 2016 00:00:00 +0000

This research develops an instructional model for implementing mixed/hybrid reality in educational environments. The model is validated through two functional prototypes.

The first prototype targets higher education: it is used in an animation class of the audiovisual arts programme and lets students modify and build kinetic structures in virtual reality using Google Cardboard.

The second prototype focuses on teaching ecosystems in primary school: an open world where students explore and complete missions in order to learn new concepts.

Biobank

Wed, 27 Apr 2016 00:00:00 +0000

A biobank is a repository that stores and manages biological samples (biospecimens) for research. Correct handling, organisation and storage are essential to its purpose, and storage conditions such as humidity and temperature are critical: if these parameters fluctuate without an adequate control plan, biological material of high scientific value is put at risk.

We built a low-cost remote monitoring system for the UNAB biobank using open-source hardware and software. It monitors temperature, humidity, door opening, alarms and power failures using environmental sensors, a custom-built microcontroller and a Raspberry Pi, plus a web interface that helps the biobank staff follow the storage conditions.

EducAR

Wed, 27 Apr 2016 00:00:00 +0000

The main motivation of this research is university dropout. First-semester students sometimes arrive with gaps in concepts studied in high school; together with the way mathematics, physics and chemistry courses are taught, this can make them lose interest in these courses, leading to low academic performance and, eventually, dropout.

We developed an augmented reality application that any teacher and student at the Universidad Autónoma de Bucaramanga (UNAB) can use as a complement to their classes, to capture students’ interest and make it easier to grasp the concepts studied. This version focuses on electromagnetic concepts: resistors, circuits and magnetic fields. With EducAR, physical phenomena and experiments can be represented with 3D models without additional lab equipment.

EducAR was built with Unity 3D (version 5.3.1), which targets both mobile and desktop devices, and the Vuforia SDK, which turns the device screen into an augmented reality display.

Good company in a journey makes the way seem shorter. — Izaak Walton