Wilson Chango

TL;DR: Four different data fusion approaches for predicting the final academic performance of university students using multiple-source, multimodal data from blended learning environments show that the best predictions are produced using ensembles and selecting the best attributes approach with discretized data.

TL;DR: The current state of the art by reviewing the main publications, the main type of fused educational data, and the data fusion approaches and techniques used in EDM/LA, as well as the main open problems, trends, and challenges in this specific research area.

TL;DR: The best predicting model is shown in order to help instructor to take remedial actions with students at risk of dropout or failing in multimodal and blended learning environments using data fusion and data mining.

TL;DR: In this paper, a study was conducted to predict university students' learning performance using different sources of performance and multimodal data from an Intelligent Tutoring System, and the results showed that the best predictions were produced using ensembles and selecting the best attributes approach with numerical data.

TL;DR: Data gathered form face recording of students' interactions with an Intelligent Tutoring System is used to detect students' emotions and determine to what extent they can predict the final students’ performance during the learning session.