Persistent Patterns in Eye Movements: A Topological Approach to Emotion Recognition
This work addresses emotion recognition for affective computing and human behavior analysis, representing an incremental application of topological methods to a specific domain.
The paper tackled emotion recognition from eye-tracking data by using a topological pipeline based on persistent homology to analyze gaze trajectories, achieving up to 75.6% accuracy on four emotion classes.
We present a topological pipeline for automated multiclass emotion recognition from eye-tracking data. Delay embeddings of gaze trajectories are analyzed using persistent homology. From the resulting persistence diagrams, we extract shape-based features such as mean persistence, maximum persistence, and entropy. A random forest classifier trained on these features achieves up to $75.6\%$ accuracy on four emotion classes, which are the quadrants the Circumplex Model of Affect. The results demonstrate that persistence diagram geometry effectively encodes discriminative gaze dynamics, suggesting a promising topological approach for affective computing and human behavior analysis.