Inclusive AI for Group Interactions: Predicting Gaze-Direction Behaviors in People with Intellectual and Developmental Disabilities

TL;DR

This paper introduces a new dataset and analysis for detecting gaze behaviors in people with intellectual disabilities, aiming to improve inclusive AI support for group interactions involving neurodiverse individuals.

Contribution

It presents the MIDD dataset, compares gaze and engagement patterns with neurotypical data, and evaluates classifiers to enhance inclusive AI systems for neurodiverse populations.

Findings

Fine-tuning on MIDD improves gaze detection performance.

Atypical gaze patterns differ significantly from neurotypical data.

Insights from therapists highlight practical implications for inclusive AI.

Abstract

Artificial agents that support human group interactions hold great promise, especially in sensitive contexts such as well-being promotion and therapeutic interventions. However, current systems struggle to mediate group interactions involving people who are not neurotypical. This limitation arises because most AI detection models (e.g., for turn-taking) are trained on data from neurotypical populations. This work takes a step toward inclusive AI by addressing the challenge of eye contact detection, a core component of non-verbal communication, with and for people with Intellectual and Developmental Disabilities. First, we introduce a new dataset, Multi-party Interaction with Intellectual and Developmental Disabilities (MIDD), capturing atypical gaze and engagement patterns. Second, we present the results of a comparative analysis with neurotypical datasets, highlighting differences in class imbalance, speaking activity, gaze distribution, and interaction dynamics. Then, we evaluate classifiers ranging from SVMs to FSFNet, showing that fine-tuning on MIDD improves performance, though notable limitations remain. Finally, we present the insights gathered through a focus group with six therapists to interpret our quantitative findings and understand the practical implications of atypical gaze and engagement patterns. Based on these results, we discuss data-driven strategies and emphasize the importance of feature choice for building more inclusive human-centered tools.