Building Learning Analysis System with GQM Methodology and ELK Stack

Abstract

With the development of Internet technology, Massive Open Online Courses (MOOCs) are becoming popular around the world, and more and more people are learning new knowledge through online learning platforms. Learners generate a lot of information on learning platforms every day, and most of the information is recorded in logs. However, it is difficult to start to extract valuable information from the huge and messy log data of learning platforms, which requires a methodology to guide and a lot of time and cost to process the data. Therefore, this research proposes a data analysis process, using the GQM (Goal Question Metric) method as a guide for the analysis process combined with the Banerjee analysis model to build a series of question lists and metrics to evaluate students’ learning behavior performance, and using the ELK Stack (Elasticsearch Logstash Kibana) as an analysis environment to solve the problem of data processing. Finally, we conduct a case study of a programming course in the OpenEdu e-learning platform to help educators transform the log data into analyzable information to understand students’ learning behaviors in the online course and to propose effective decisions for improving learning outcomes.