Game Learning Analytics for Serious Game Scoring

Abstract

Game Learning Analytics (GLA) is the collection, analysis and visualization of player interactions within serious games. This interaction provides valuable insights into learning outcomes at the expense of a massive amount of data collected and complex analysis procedures. Instead of collecting detailed player interactions within serious games, we propose to capture only the outcomes of each serious game. That is, was the game goal achieved, what was the cost of achieving the game goal and what knowledge or resources did the player need for achieving the game goal? The focus of our GLA is on evaluative indicators (time and effort in achieving the game goal) collected over multiple game sessions and multiple players. Such a collection of game outcomes would enable us to observe performance improvements of players who solve the same game in order to optimize performance and also to determine learning outcomes of single players, learning outcomes of a cohort of players and learning outcomes of how a player relates to the other players in a cohort. From serious games we want to find out who has specific knowledge and skills in order to use learning patterns. First, to improve operational performance. Second, to identify individuals who may successfully handle any emergency situations based on skills obtained from playing serious games. Third, to identify useful serious games with respect to training.