An Affect Detector Model For Gamers on a Role-Playing Game Through Mouse Movements

Abstract

In this study, the researchers have modeled an affect detector based on the mouse movements that they have gathered while the respondents, as casual or core gamers, are playing the role-playing game. After being able to gather and prepare the data with the help of several software and tools, features such as the number of mouse clicks and distance moved were extracted and developed a models through the classifiers: Decision Tree, Random Forest, and J48. Given the parameters and features included, the chosen model was used to create a prototype. The prototype developed can be of use to game developers in game testing by giving them the ability to monitor the emotions of their end-users. This will then correspond to valuable data to apply for game design improvement.