Co-Located Human-Human Interaction Analysis using Nonverbal Cues: A Survey

TL;DR

This survey reviews recent computational methods for analyzing co-located human interactions using nonverbal cues, covering social traits, roles, and dynamics across various settings, highlighting current challenges and future directions.

Contribution

It provides the broadest overview of nonverbal cue analysis in co-located interactions, including datasets, methodologies, and future AI-driven research avenues.

Findings

Support vector machines are commonly used for analysis.

Multimodal features outperform unimodal approaches.

Deep learning improves performance but faces limitations.

Abstract

Automated co-located human-human interaction analysis has been addressed by the use of nonverbal communication as measurable evidence of social and psychological phenomena. We survey the computing studies (since 2010) detecting phenomena related to social traits (e.g., leadership, dominance, personality traits), social roles/relations, and interaction dynamics (e.g., group cohesion, engagement, rapport). Our target is to identify the nonverbal cues and computational methodologies resulting in effective performance. This survey differs from its counterparts by involving the widest spectrum of social phenomena and interaction settings (free-standing conversations, meetings, dyads, and crowds). We also present a comprehensive summary of the related datasets and outline future research directions which are regarding the implementation of artificial intelligence, dataset curation, and privacy-preserving interaction analysis. Some major observations are: the most often used nonverbal cue, computational method, interaction environment, and sensing approach are speaking activity, support vector machines, and meetings composed of 3-4 persons equipped with microphones and cameras, respectively; multimodal features are prominently performing better; deep learning architectures showed improved performance in overall, but there exist many phenomena whose detection has never been implemented through deep models. We also identified several limitations such as the lack of scalable benchmarks, annotation reliability tests, cross-dataset experiments, and explainability analysis.