Assessing the suitability of student interactions from Moodle data logs as predictors of cross-curricular competencies

Abstract

In the past decades, online learning has transformed the educational landscape with the emergence of new ways to learn. This fact, together with recent changes in educational policy in Europe aiming to facilitate the incorporation of graduate students to the labor market, has provoked a shift on the delivery of instruction and on the role played by teachers and students, stressing the need for development of both basic and cross-curricular competencies. In parallel, the last years have witnessed the emergence of new educational disciplines that can take advantage of the information retrieved by technology-based online education in order to improve instruction, such as learning analytics.This study explores the applicability of learning analytics for prediction of development of two crosscurricular competencies -teamwork and commitment -based on the analysis of Moodle interaction data logs in a Master's Degree program at Universidad a Distancia de Madrid (UDIMA) where the students were education professionals. The results from the study question the suitability of a general interaction-based approach and show no relation between online activity indicators and teamwork and commitment acquisition. The discussion of results includes multiple recommendations for further research on this topic.

Can online student performance be forecasted by learning analytics?

“…In fact, only two groups of researchers (Agudo-Peregrina et al, 2014;Gomez-Aguilar et al, 2015) found any statistically significant correlation relationship between student online activity reported in learning analytics and academic performance. More than one researcher confirmed there was no statistically significant relationship between learning analytics, LMS activity data, and student learning outcomes (Iglesias-Pradas, Ruiz-de-Azcarate and Agudo-Peregrina, 2015). Therefore, more studies are needed to test if learning analytics data could relate to or predict student performance.…”

“…The four common units of analysis used with online student activity in learning analytics studies (Agudo-Peregrina et al, 2014;Iglesias-Pradas, Ruiz-de-Azcarate and Agudo-Peregrina, 2015), as outlined below:…”

“…The authors of 11 relevant studies not only published some benefits in peer-reviewed scholarly journals but they also cited many problems when trying to assess student learning through combinations of learning analytics, learning management system (LMS) activity data logs, and graded performance results (Agudo-Peregrina et al, 2014;Fidalgo-Blanco et al, 2015;Gomez-Aguilar et al, 2015;Iglesias-Pradas, Ruiz-de-Azcarate and Agudo-Peregrina, 2015;Nieto Acevedo and Montenegro Maran, 2015;Reyes, 2015;Ruiparez-Valiente et al, 2015;Scheffel et al, 2014;Xing et al, 2015;Yahya, Messoussi and Touahni, 2015).…”

“…A few pertinent empirical studies have uncovered some relationships between student performance and online activity in Moodle (Dierenfeld and Merceron, 2014;Ferguson and Buckingham-Shum, 2012;Hatala, Gasevic and Joksimovic, 2014;Iglesias-Pradas, Ruiz-de-Azcarate and Agudo-Peregrina, 2015;Strang, 2013b). Moodle, the popular open source LMS developed in Australia, now features a learning analytics module called 'engagement analytics' (Dimopoulos, 2015, para.…”

Learning Analytics focused on student behavior. Case study: dropout in distance learning institutions

“…In the last years, we have seen that new areas of study are emerging in the educational domain, for example the Educational Data Mining (EDM) and LA [11]. In general, there are a lot of papers in these domains, focused on course level analysis, predictive models, semantic content analysis, sentimental analysis, and social network analysis, in the general educational context [1], [12], [13], [14], [15], [16], [17], [18], [22], [26], [33].…”