Saved in:
Bibliographic Details
Main Authors: Niksa, Arsha, Zare, Hooman, Shahrabi, Ali, Hatami, Hanieh, Razvan, Mohammadreza
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.17450
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916858957922304
author Niksa, Arsha
Zare, Hooman
Shahrabi, Ali
Hatami, Hanieh
Razvan, Mohammadreza
author_facet Niksa, Arsha
Zare, Hooman
Shahrabi, Ali
Hatami, Hanieh
Razvan, Mohammadreza
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_17450
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Persistent Patterns in Eye Movements: A Topological Approach to Emotion Recognition
Niksa, Arsha
Zare, Hooman
Shahrabi, Ali
Hatami, Hanieh
Razvan, Mohammadreza
Machine Learning
55N31
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.
title Persistent Patterns in Eye Movements: A Topological Approach to Emotion Recognition
topic Machine Learning
55N31
url https://arxiv.org/abs/2507.17450