A2E 2019 Abstracts

Full Papers
Paper Nr: 3

Predicting Students’ Performance in a Virtual Experience for Project Management Learning


Ana González-Marcos, Rubén Olarte-Valentín, Joaquín Ordieres-Meré and Fernando Alba-Elías

Abstract: This work presents a predictive analysis of the academic performance of students enrolled in project management courses in two different engineering degree programs. Data were gathered from a virtual learning environment that was designed to support the specific needs of the proposed learning experience. The analyzed data included individual attributes related to communication, time, resources, information and documentation activity, as well as behavioral assessment. Also, students’ marks on two exams that took place during the first half of the course were considered as input variables of the predictive models. Results obtained using several regression and classification algorithms –support vector machines, random forests, and gradient boosted trees– confirm the usefulness of Educational Data Mining to predict students’ performance. These models can be used for early identification of weak students who will be at risk in order to take early actions to prevent these students from failure.

Paper Nr: 4

Using Learning Analytics within an e-Assessment Platform for a TransFormative Evaluation in Bilingual Contexts


Samira ElAtia and Eivenlour David

Abstract: Learning Analytics (LA) has the potential to be used as a unique and viable learning, teaching and research tool to analyze data from longitudinal assessment. The online language assessment platform, Profil Linguistique, is an innovative and useful tool, in that (1) it adapts to students learning abilities and progress and gives them the chance to monitor their progress, (2) it uses data mining to provide reports to teachers and administration who subsequently adapt the general language program in a Canadian university. From a theoretical point of view, the testing construct identified as the basis of this online assessment tool would engage students in progressing in their language competence in parallel with the courses they are taking. It is a provocative and unique way to integrate and look at assessment as a teaching tool by using LA.

Paper Nr: 6

Collecting and Analysing Learners Data in a Massive Open Online Course for Mathematics


Ana Azevedo, Marisa Oliveira, Alcinda Barreiras, Jose M. Azevedo, Graça Marcos and Hermínia Ferreira

Abstract: Massive Open Online Courses (MOOCs) are online courses with an unlimited number of participants and no entry requirements. Due to their massive and open nature, MOOCs have a high potential to offer access to education to millions of people worldwide. However, there are several challenges in MOOCs such as huge drop-out rates, improper automated assessments, diverse student engagement, and attention, etc. Learning Analytics is “the measurement, collection, analysis, and reporting of data about learners and their contexts, for purposes of understanding and optimizing learning and the environments in which it occurs” (Society of Learning Analytics Research (SoLAR)) which can help us to contain such issues. This paper presents an initial analysis, using descriptive analytics, of the students’ activity in a MOOC for Mathematics. The analysis allowed the developers of the course to better understand some of the limitations and also some of the strengths of the course in order to continuously adapt it to the users’ needs and interests.

Short Papers
Paper Nr: 2

Rule Induction Algorithms Applied in Educational Data Set


Walisson Carvalho, Cristiane Nobre and Luis Zarate

Abstract: This article presents the application of three induction rules algorithm: OneR, RIPPER and PART in an educational data set aiming to explain the main factors that lead students to be succeed or failure in online course. The dataset used to develop this article was extracted from the log of activities of engineering students that enrolled in a 20 weeks course of Algorithm offered online. The students used Learning Management System, Moodle. The dataset was preprocessed and then it was applied the algorithms into it. As result it was observed that students who begin earlier an assignment improve their probability of succeed.