Evaluation of In-game Experience and Neural Analysis of Motivational Purposes in Video Games
In a groundbreaking study, researchers have developed a method to predict players' goal orientations in video games by analyzing brain activity, physiological signals, and contextual gameplay data. This innovative approach could revolutionize the field of video game design and player motivation research.
The study employs Electroencephalography (EEG) to measure brain activity during gameplay, providing insights into neural activity patterns related to attention, decision-making, stress, and cognitive load. For instance, EEG studies show significant modulations in beta, alpha, and delta waves linked to esports play, reflecting changes in focus and decision mechanisms that correlate with cognitive effort and goal-directed behavior in gamers.
Physiological signals like heart rate and skin conductance are also collected, indicating arousal and stress levels. These biological markers help refine the prediction of motivational states during gameplay, capturing the player's underlying mental and emotional effort.
Machine learning models are then trained on features extracted from these data, alongside contextual data such as player profiles and game situations. These models classify or predict cognitive states such as cognitive effort, engagement, or emotional responses with moderate to good accuracy. Combining multiple signal modalities improves robustness and predictive power.
In video games, integrating these data streams allows models to infer players' goal orientations—such as achievement focus, exploration, or social interaction—by analyzing patterns of neural activation, physiological responses, and contextual gameplay data. For example, distinct EEG patterns may emerge when players pursue competitive goals versus exploratory or social goals, and machine learning algorithms can learn these mappings to generate real-time or post-game predictions of player motivation.
The resulting machine learning model adapts the game based on the predicted players' motivational goal orientations, potentially enhancing player engagement and personalizing the gaming experience. The study uses the GameFlow questionnaire to characterize players' performance-approach and mastery goals in playing video games, and Frontal Alpha Asymmetry (FAA) to assess the player's approach/withdrawal behavior within a game scene.
While the study does not specify the particular video game used, it does analyse player's goal orientations motivation in different video-game scenes. The evaluation of player experience is done through subjective measures (questionnaire) and objective measures (electroencephalography - EEG).
The study does not provide information about the specific OCC variables used, the specific machine learning techniques employed, or the specific performance metrics used to evaluate the effectiveness of the player model. However, it highlights the potential applications and implications of the adaptive game in the field of video game design or player motivation research.
In summary, this study presents an innovative approach to predicting player goal orientations in video games by leveraging brain activity and peripheral physiological indicators. This integrative method could support applications in adaptive game design, personalized training, or player engagement enhancement.
The study's methodology includes the use of technology such as Electroencephalography (EEG) to analyze brain activity and physiological signals like heart rate, which fall under the category of gadgets. These technological tools help predict players' goal orientations in video games, adding significant potential for advancements in video game design and player motivation research. The machine learning models, trained on the aforementioned data, are instrumental in inferring gamers' goal orientations, demonstrating the effective fusion of technology and game design.
