• Publications
  • Influence
What do students do on-line? Modeling students' interactions to improve their learning experience
The types of interactions were used to personalize gamification elements named missions, and generated the students’ interactional profile (a model of their interactions) to assist teachers and tutors (education professionals) decision-making, regarding their students learning experience. Expand
A BDI approach to infer student's emotions in an intelligent learning environment
The use of mental states approach, more specifically the belief-desire-intention (BDI) model, is described to implement the process of affective diagnosis in an educational environment to infer the learner's emotions from his actions in the system interface. Expand
Rule-based expert systems to support step-by-step guidance in algebraic problem solving: The case of the tutor PAT2Math
This paper describes the expert system (ES) module of an Algebra ITS, called PAT2Math, and describes how it was reduced from O(nd) to O(d), where n is the number of rules in the knowledge base, by implementing some meta-rules that aim at inferring the operations students applied in order to produce a step. Expand
Towards Reducing Cognitive Load and Enhancing Usability through a Reduced Graphical User Interface for a Dynamic Geometry System: An Experimental Study
The experimental results indicate that an interface that hides advanced and extraneous features helps novice users to perform slightly better than novice users using a complete interface, which makes users more productive than a reduced interface. Expand
Using an Animated Pedagogical Agent to Interact Affectively with the Student
................................................................................................................. 10
An Analysis of Hierarchical Text Classification Using Word Embeddings
An analysis indicates that using word embeddings and its flavors is a very promising approach for HTC. Expand
Improving pedagogical recommendations by classifying students according to their interactional behavior in a gamified learning environment
A way to classify students from a gamified online learning environment according to their interactions is presented, and the results are used to create and recommend "missions" - a gamification element that contains challenging tasks to keep students engaged. Expand
Evaluating the affective tactics of an emotional pedagogical agent
This paper presents a quantitative and qualitative evaluation of a lifelike and emotional pedagogical agent, called Pat, which has the goal of inferring students' emotions and applying affective tactics in order to adapt the learning environment. Expand
Affective states in computer-supported collaborative learning: Studying the past to drive the future
Three main challenges to be addressed by the community in the next decade for an adequate incorporation of affective states in CSCL environments: emotional awareness, orchestration of students' interaction and group formation are identified. Expand
Developing web fully-integrated conversational assistant agents
This paper describes a framework, called Divalite, dedicated to the development of Web-based Embodied Conversational Agents (ECAs) for research purposes and presents the architecture and the DOM-integration of the virtual characters. Expand