Recomendação de objetos de aprendizagem baseada em estilos de aprendizagem e traços de personalidade.

Abstract

Learning Objects (LO) used in on-site courses or distance learning are stored in computing environments used in the teaching-learning process, and tend to grow their numbers over time. Although Recommendation Systems (RS) are currently being used successfully to recommend items in various fields, the educational context has special features (for example, pedagogical issues) which make the creation of such systems even more challenging. The Personality — which can be defined as a consistent pattern of behavior originated internally in an individual — influences the decision-making process. In addition, there is concern with the Learning Styles (LS), through which learners perceive, process, and retain information. Based on the above considerations, this research aims to propose a model of RS for Learning (RSL) using the concepts of LS and Personality in building the profile of students, in order to make a custom selection of LO to be recommended. Although it is still challenging to create RSL involving the extraction and insertion of psychological concepts as previously mentioned, in this dissertation a model that recommends LO is presented and evaluated, following the IEEE LOM standard, based on the extraction of LS via Index of Learning Styles and of Personality Traits (PT) via Five Labs, an online tool for semantic analysis of Facebook posts. Considering metrics known in RS, an experiment with computer science students indicated that the proposed model provided similar or better results when compared to other recommendation approaches. Therefore, the proposed approach seems promising for personalized content recommendation in the education field.