Abstract:

E-assessment is the ICT driven evaluation process in e-learning. The main reasons for the use of e-assessment for higher education online are: the increase in student retention, improving the quality of feedback, flexibility for distance learning objectivity in qualifying and the most efficient use of virtual learning environments. While the disadvantages are: problems of plagiarism, accessibility, reliability and validity of the assessment and identification of students. There are also barriers associated with software use, interoperability, integration with existing systems, scalability, security and accessibility.

Learning analytics can be defined as 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. The availability of data on the interactions of online students is an opportunity to improve learning processes in formal education. Data produced by the student provides valuable information about the reality of the learning process and suggests opportunities for improvement to educators. Among others, we can identify students at risk, assist students in achieving goals, and provide students with knowledge about their own learning habits and with recommendations for improvement.

Key elements of an e-assessment system are formative assessment model, continuous interaction and personalized feedback. Since the interaction is a key element, the capture and analysis of the interaction also becomes a fundamental element. The information obtained from the data analysis will allow knowing the student patrons during the course and checking if they correlate to the achievement of skills, the solving activities, the feedback received, and the obtained grades.

For this, focusing on assessment, feedback will be analysed based on interactivity, engagement and personalization of feedback and activities. Under this, a simulator can be developed which can be able to provide automatic feedback to students based on their level of interactivity which is personalized for each student. Also, the activities to be provided to students will be personalized based on their level of ability. As a result of this, a framework for assessment analytics can be developed.

This research focuses on the e-assessment analytics for STEM, ie the application of learning analytics techniques to improve e-assessment in the field of STEM subjects. The study will be based on the tool ALURA, an e- assessment system for Logic courses at the Computer Science Department of the Open University of Catalonia, but it will look for generalizable results in the field of STEM subjects. Thus, this real case research focuses on the analysis of student activity in relation to the process of e-assessment in the Logic course.

The overall objective is to propose a general framework for e-assessment analytics in the context of STEM courses in Higher Education.

Keywords:

E-assessment, learning analytics, higher education, STEM.