Automatic Analytics Model for Learning Skills Analysis Using Game Player Data and Robotic Process Automation in a Serious Game for Education

Utilizing serious games as a learning support tool can motivate students' interest in learning and improving their educational skills. The effectiveness of serious games in learning is usually assessed with traditional paper-based pre-posttests tools and predefined learning outcomes. However, serious game player data have proven to be a useful tool to measure the effect of games on student knowledge, learning skills and to evaluate their academic performance and achievements. In this paper, we introduce a new model for automatically read game player data and provide an analysis of game player learning skills. The model is composed of game learning analytics, robotic process automation, and the statistical analysis package to assess the effect based on game players' data. The model used the plant kingdom unit in the science book of grade eight students. The learning outcomes, content, and learning skills are considered in developing game content. The model tested on a sample of 15 students aged 13–14 years from Palestinian public schools. The students played the game four times, and the game's player data sent automatically into the game database and analyzed. The model provides an efficient pre-posttest assessment tool based on the game players dataset. The results showed a significant improvement in learning skills performance measures after comparing the results of the first session with the fourth session.