Supporting competency-assessment through a learning analytics approach using enriched rubrics

Universities have increasingly emphasized competencies as central elements of students’ development. However, the assessment of these competencies is not an easy task. The availability of data that learners generate in computer mediated learning offers great potential to study how learning takes place, and thus, to gather evidences for competency-assessment using enriched rubrics. The lack of data interoperability and the decentralization of those educational applications set out a challenge to exploit trace data. To face these problems we have designed and developed SCALA (Scalable Competence Assessment through a Learning Analytics approach), an analytics system that integrates usage -how the user interacts with resources- and social -how students and teachers interact among them-trace data to support competency assessment. The case study of SCALA presents teachers a dashboard with enriched rubrics of blended datasets obtained from six assessment learning activities, performed with a group of 28 students working teamwork competency. In terms of knowledge discovery, we obtain results applying clustering and association rule mining algorithms. Thus, we provide a visual analytics tool ready to support competency-assessment.