Plan Ceibal is a universal public policy implemented in Uruguay since 2010, it is part of the global initiative One Laptop per Child (OLPC, 2005). This program consists of providing every student and teacher in kindergarten, primary and middle school with a laptop or tablet and internet access in the school. Plan Ceibal has covered all public schools in the country and it has improved equality of access to technology, as well as ensured internet access in all public schools.
Different data sets were combined, students and teachers activities registered in the Learning Management System (LMS) and student’s performance in national standardized tests. These data set were used to define student’s engagement indexes, different use dimensions in the LMS were considered: motivation, creativity, velocity and performance. Understanding the key drivers of LMS use is really important to define educational policies based on evidence. Models for LMS use are fitted for several regional levels.
Additionally, statistical learning methods were fitted to predict student’s performance in national standardized test using as predictor variables different constructed usage indexes from the LMS platform. Some of the main challenges for this task are related to how to incorporate sub-grouping data structure into machine learning algorithms which are usually developed for independent observations datasets and also how to transform the data into information for the model.
Initial results suggest that geographical region is the main driver of the technology usage in the classroom. Other factors such as the socio-economic context of the primary school or the class grade are significant but less relevant.
