Data Mining Framework to Analyze the Evolution of Computational Thinking Skills in Game Building Workshops

Computational thinking has become a required capability in the student learning process, and digital games as a teaching approach have presented promising educational results in the development of this competence. However, properly evaluating the effectiveness and, consequently, student progress in a course using games is still a challenge. One of the most widely implemented ways of evaluation is with an automated analysis of the code developed in the classes during the construction of digital games. Nevertheless, this topic has not yet been explored in aspects such as incremental learning, the model and teaching environment and the influences of acquiring skills and competencies of computational thinking. Motivated by this knowledge gap, this paper introduces a framework proposal to analyze the evolution of computational thinking skills in digital games classes. The framework is based on a data mining technique that aims to facilitate the discovery process of the patterns and behaviors that lead to the acquisition of computational thinking skills, by analyzing clusters with an unsupervised neural network of self-organizing maps (SOM) for this purpose. The framework is composed of a collection of processes and practices structured in data collection, data preprocessing, data analysis, and data visualization. A case study, using Scratch, was executed to validate this approach. The results point to the viability of the framework, highlighting the use of the visual exploratory data analysis, through the SOM maps, as an efficient tool to observe the acquisition of computational thinking skills by the student in an incremental course.