Application of Learning Analytics in a Remote Lab Context: A Systematic Literature Review

Remote Laboratories (RLs) are software and hardware tools that allow students to remotely perform real experiments by means of an online system or platform. They represent an evolution in the learning process by making the execution of real-world experiments accessible for many students at distance. Learning Analytics (LAs), by contrast, is the research area concerned with the collection, measurement, analysis and reporting of data associated with learning and its outcomes. The application of LA to RLs leads to a better understanding and planning of the main teaching and learning processes, and their outcomes. This paper aims at providing a systematic review of the application of learning analytics to remote laboratories, thus building an up-to-date body of knowledge for researchers and professionals interested in the application of digital technologies into the educational context. This research follows a procedure based on three main steps: planning, conducting, and reporting. We searched seven STEM (Science, Technology, Engineering and Mathematics) databases with two search queries. The retrieved documents were analyzed under the umbrella of five research questions, and a comprehensive organization and structure of the surveyed literature was proposed. The results obtained showed eight main RL platforms/systems (NetLab, WebLab-Deusto, Go-Lab, FORGE, Lab4CE, GOLDI, and MOOLs-based), and four categories of data to be retrieved and analyzed by LA methods. Also, we identified five types of metrics usually used to measure the outcome of the learning process, and five learning outcomes. This paper provided an up-to-date systematic review on the use of learning analytics within the remote lab context. We explored platforms, use cases, data retrieved, performance metrics, analysis methods, and learning outcomes. Among the many conclusions, it is possible to stress that the application of LA to RLs aids in the visualization of the learner's strengths and difficulties during a RL experiment, the automatic evaluation of the experiment, and efficient feedback.