AffectiveTDA: Using Topological Data Analysis to Improve Analysis and Explainability in Affective Computing

TL;DR

This paper introduces AffectiveTDA, a novel method using Topological Data Analysis to enhance the understanding and explainability of facial expressions in emotion recognition, capturing structural patterns across emotions and individuals.

Contribution

It applies TDA to affective computing, demonstrating its effectiveness in capturing emotion-related facial pose structures and improving interpretability.

Findings

Topology-based approach captures known emotion patterns

Distinguishes between different emotions and individuals

Enhances robustness and explainability in emotion recognition

Abstract

We present an approach utilizing Topological Data Analysis to study the structure of face poses used in affective computing, i.e., the process of recognizing human emotion. The approach uses a conditional comparison of different emotions, both respective and irrespective of time, with multiple topological distance metrics, dimension reduction techniques, and face subsections (e.g., eyes, nose, mouth, etc.). The results confirm that our topology-based approach captures known patterns, distinctions between emotions, and distinctions between individuals, which is an important step towards more robust and explainable emotion recognition by machines.