A Proposed Audiovisual Quality Assessment Model Associated with Multiplayer Online Battle Arena Game: A Pilot Study with ROV

Abstract

This study proposes an audiovisual quality assessment model for a popular gaming scenario, called the Multiplayer Online Battle Arena (MOBA) gaming. The subjective data about voice quality during conversation of the game players, the video quality, the overall quality, and the weighted percentage of voice and video have been gathered from 40 participants who competed in a small competition event of the Garena ROV (Arena of Valor) in Thailand. Then, three quarters of data have been used to create the model, while the last quarter of data has been used for model evaluation. After creating the model, it has been evaluated using Mean Absolute Percentage Error (MAPE) with three audiovisual quality evaluation models that provide good performances. It has been found that the proposed audiovisual quality assessment model provides better performance than previous works with MAPE of 6.16 %, while other models provide MAPE of 7.67 - 8.54%. Therefore, this evidence supports that the proposed model could be applied for evaluation of audiovisual quality based on the MOBA gaming scenario.