Pseudo-Label Augmentation for Affect Sensing in Small Collaborative Groups
Quick summary
arXiv:2609.16077v1 Announce Type: cross Abstract: Physiological affect sensing in naturalistic group interaction is often limited by sparse labels rather than sensor data: wearable devices produce many time windows, while self-reports are collected only a few times per session. Using GroupAffect-4, a four-person collaborative dataset with wearable physiology, eye tracking, Big Five personality, and post-task VAD labels, we study pseudo-label augmentation for affect sensing under sparse supervision. We compare no augmentation, Gaussian Process pseudo-labelling, personality-aware trust weighting
Key takeaways
- arXiv:2609.16077v1 Announce Type: cross Abstract: Physiological affect sensing in naturalistic group interaction is often limited by sparse labels rather than sensor data: wearable devices produce many time windows, while self-reports are collected only a few times per session.
- Using GroupAffect-4, a four-person collaborative dataset with wearable physiology, eye tracking, Big Five personality, and post-task VAD labels, we study pseudo-label augmentation for affect sensing under sparse supervision.
- We compare no augmentation, Gaussian Process pseudo-labelling, personality-aware trust weighting
Why it matters
“Pseudo-Label Augmentation for Affect Sensing in Small Collaborative Groups” highlights the need for repeatable measurement rather than a single impressive demonstration. Independent validation across datasets and clearly stated limitations determine whether a result can guide product decisions.
Member comments