Assessing In-Game Scenes and Forecasting Prevailing Player Emotions
In a groundbreaking development, researchers have unveiled EMOGRAPH, a system designed to analyse and predict player emotions during gameplay. This innovative tool, known as the Emotional Graph, holds immense potential for expanding the possibilities in game design.
EMOGRAPH is a multifaceted system that integrates multiple data streams, including eye movements, facial expressions, subjective measures, objective measures, and machine learning algorithms.
The system's primary focus is on capturing how players visually and emotionally react during gameplay. Changes in pupil dilation, gaze patterns, and facial muscle activity provide indicators of emotional states such as fear, surprise, or stress. To complement this, self-reported emotional data from players, often through questionnaires or Likert scale-based inputs, add a personal insight into the player’s felt emotions.
Physiological data like heart rate or galvanic skin response also contribute to the objective measures, providing quantifiable indicators of arousal or stress. The combined data is then analysed by machine learning algorithms, which learn to correlate specific input features with emotional states, enabling real-time prediction of player emotions during gameplay.
The emotion prediction approach in EMOGRAPH is based on the design goals of game scenes, as defined by OCC variables from the model of emotions' cognitive evaluation by Ortony, Clore, and Collins. This means that EMOGRAPH's system annotates game objects with dominant emotions based on the combination of eye movements and facial expressions.
The effectiveness of EMOGRAPH was demonstrated in an experiment involving 21 participants playing the horror game "Outlast". The results show that the system provides valuable insights into user experience and accurately predicts player emotions. These promising prediction results could widen possibilities in game design, allowing developers to create more immersive and emotionally engaging experiences for players.
In conclusion, EMOGRAPH represents a significant leap forward in the field of gaming. By integrating multiple data streams, this system robustly and accurately assesses and predicts player emotions, accounting for both external behaviour and internal feelings, which is particularly useful for the intense emotional environment of horror games like Outlast.
- The inclusion of eye tracking technology and artificial-intelligence algorithms in EMOGRAPH enables the system to predict player emotions during intense football matches, suggesting potential applications for improving player performance and spectator experience.
- As EMOGRAPH expands its potential for predicting player emotions in various sports settings, future research could investigate how this technology might be utilized within football, aiming to create more emotionally engaging experiences for both players and spectators.
