ToTCompute: A Novel EEG-Based TimeOnTask Threshold Computation Mechanism for Engagement Modelling and Monitoring

摘要: Engagement influences participation, progression and retention in game-based e-learning (GBeL). Therefore, GBeL systems should engage the players order to support them maximize their learning outcomes, provide with adequate feedback maintain motivation. Innovative engagement monitoring solutions based on players’ behaviour are needed enable a non-disturbing way, without interrupting game-play game flow. Furthermore, generic metrics automatic mechanisms for modelling needed. One important metric that was used is TimeOnTask, which represents duration of time required by player complete task. This paper proposes ToTCompute (TimeOnTask Threshold Computation), novel mechanism automatically computes - task-dependent manner TimeOnTask threshold values after student decreases given percentage from his initial level (e.g., 2 min will fall 10 % level). In this way enables at higher granularity further engagement-based adaptation systems. makes use game-playing information EEG signals collected through an testing session. The results experimental case study have shown can be compute metric, explains up 76.2 variance change. confirmed usefulness as value highly task-dependent, setting its manually multiple tasks would laborious process.