A Symbolic Machine Learning Approach for Cybersickness Potential-Cause Estimation
Virtual reality (VR) and head-mounted displays are constantly gaining popularity in various fields such as education, military, entertainment, and bio/medical informatics. Although such technologies provide a high sense of immersion, they can also trigger symptoms of discomfort. This condition is called cybersickness (CS) and is quite popular in recent publications in the virtual reality context. This work proposes a novel experimental analysis using symbolic machine learning that ranks potential causes for CS. We estimate the CS causes and rank them according to their impact on the classification capabilities of CS. The experiments are performed using two distinct virtual reality games. We were able to identify that acceleration triggered cybersickness more frequently in a race game in contrast to a flight game. Furthermore, participants less experienced with VR are more prone to feel discomfort and this variable has a greater impact in the race game in contrast to the flight game, where the acceleration is not controlled by the user.