Proposal of a system of indicators to assess teamwork using log-based learning analytics

One of the main lines of research in the field of learning analytics focuses on the identification of adequate data extracted from Learning Management Systems’ (LMS) databases that may help predicting different behaviors and outcomes, such as academic achievement or student performance. Prior research has investigated these indicators at an individual level. The situation is more complex in collaborative settings involving teamwork, such as project-based learning, where student assessment considers the group as a single entity, disregard of individual contributions to the team. Furthermore, most often only the final deliverable is taken into account when assessing teamwork in collaborative learning, leading to a loss of perspective about the whole process and whether or not teamwork is effectively happening. This research aims to provide a comprehensive selection of log-based information from LMS databases that could serve as potential indicators to perform learning analytics and assess teamwork in online learning. The proposal of this novel and theory-grounded framework understands the multidimensional nature of teamwork, considers different sets of indicators for each of its dimensions—communication, cooperation, coordination, and monitoring and tracking—and incorporates the temporal dimension of activity data. This proposal sets the basis for future software development to effectively transform LMS log-based data and provide actionable measures of teamwork using