AffectAI-Capture: A Reproducible Multimodal Protocol for Small-Group Meeting Research

2026-05-19

AI Summary

Existing research lacks reproducible multimodal data collection protocols, hindering systematic investigation of affective states, behaviors, and interaction dynamics in small-group meetings. This work proposes and implements a standardized protocol that integrates eye tracking, wearable physiological sensors, multichannel audio, multi-view video, event logging, and structured self-reports, with all modalities synchronized to a unified timeline. The protocol rigorously specifies task design, sensor placement, time referencing, and data packaging procedures to ensure consistency and interoperability. It thereby enables standardized affective computing and meeting analysis across studies. Benchmark evaluations confirm high audio fidelity and precise video synchronization, while preliminary data collection demonstrates the protocol’s technical feasibility and data coherence.

Abstract

We present AffectAI-Capture, a protocol for collecting synchronized multimodal data in four-person meeting-like interactions, combining eye tracking, wearable physiology, close-talk and room audio, multi-view video, event logging, and structured self-report. Sessions use fixed task blocks grounded in established group-interaction paradigms, while acquisition and post-processing are organized around a single authoritative event timeline and standardized outputs. We describe the experimental rationale, synchronization philosophy, data organization, and practical trade-offs. Pilot-level validation of audio quality and video synchronization has been conducted using controlled bench tests; full protocol sessions with participants remain ongoing work. The contribution is a reproducible protocol architecture linking task design, instrumentation, timing provenance, and data packaging for affective, behavioral, and meeting-analytics research.

Problem

• multimodal data
• small-group meetings
• synchronization
• reproducible protocol
• affective computing

Innovation

• multimodal synchronization
• reproducible protocol
• group interaction
• event timeline
• affective computing