Patrícia Takaki

The present paper aims to identify the contributions of Information Science (IS) and Computer Science (CS) to meet the informational needs of the educational context. The methodology used is exploratory, descriptive, and applied. A qualitative approach is used to process data retrieved through bibliographic research on data science applied to education. The study brought together the theoretical and practical contributions of IS and CS techniques capable of addressing the main informational challenges of educational environments reported in the literature. The preliminary results obtained consist of connections between concepts and techniques from the two knowledge areas that propose solutions for informational needs in education. Data mining, fuzzy logic, natural computing, text mining, data warehouse, ontologies, semantic web, and information retrieval were the most evident contributions identified when analyzing the demands of students, teachers, and managers. The conclusion reached is that articulating interdisciplinary knowledge of CS and IS in proposing data-driven approaches in the educational context is possible and necessary. These contributions proved capable of dealing with the challenge of supporting education in different ways by enabling even more robust theoretical and methodological solutions.

Academic failure is a crucial problem that affects not only students but also institutions and countries. Lack of success in the educational process can lead to health and social disorders and economic losses. Consequently, predicting in advance the occurrence of this event is a good prevention and mitigation strategy. This work proposes a framework to evaluate machine learning-based predictive models of academic failure, to facilitate early pedagogical interventions. We took a Brazilian undergraduate course in the distance learning modality as a case study. We run seven classification models on normalized datasets, which comprised grades for three weeks of classes for a total of six weeks. Since it is an imbalanced-data context, adopting a single metric to identify the best predictive model of student failure would not be efficient. Therefore, the proposed framework considers 11 metrics generated by the classifiers run and the application of exclusion and ordering criteria to produce a list of best predictors. Finally, we discussed and presented some possible applications for minimizing the students’ failure.