Enregistré dans:
Détails bibliographiques
Auteurs principaux: Ahmed, Md Sabbir, Petz, Kaitlyn Dorothy, French, Noah, Lakhtakia, Tanvi, Sangani, Aayushi, Rucker, Mark, Chen, Xinyu, Teachman, Bethany A., Barnes, Laura E.
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2602.22085
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916032510164992
author Ahmed, Md Sabbir
Petz, Kaitlyn Dorothy
French, Noah
Lakhtakia, Tanvi
Sangani, Aayushi
Rucker, Mark
Chen, Xinyu
Teachman, Bethany A.
Barnes, Laura E.
author_facet Ahmed, Md Sabbir
Petz, Kaitlyn Dorothy
French, Noah
Lakhtakia, Tanvi
Sangani, Aayushi
Rucker, Mark
Chen, Xinyu
Teachman, Bethany A.
Barnes, Laura E.
contents Social interactions are fundamental to well-being, yet automatically detecting them in daily life-particularly using wearables-remains underexplored. Most existing systems are evaluated in controlled settings, focus primarily on in-person interactions, or rely on restrictive assumptions (e.g., requiring multiple speakers within fixed temporal windows), limiting generalizability to real-world use. We present an on-watch interaction detection system designed to capture diverse interactions in naturalistic settings. A core component is a foreground speech detector trained on a public dataset. Evaluated on over 100,000 labeled foreground speech and background sound instances, the detector achieves a balanced accuracy of 85.51%, outperforming prior work by 5.11%. We evaluated the system in a real-world deployment (N=38), with over 900 hours of total smartwatch wear time. The system detected 1,691 interactions, 77.28% were confirmed via participant self-report, with durations ranging from under one minute to over one hour. Among correct detections, 81.45% were in-person, 15.7% virtual, and 1.85% hybrid. We further developed a 15-second window-level audio-only model that enables faster interaction prediction, achieving a balanced accuracy of 90.39% and a sensitivity of 91.01% on 33,698 labeled windows. These results demonstrate the feasibility of real-world interaction sensing and open the door to adaptive, context-aware systems responding to users' dynamic social environments.
format Preprint
id arxiv_https___arxiv_org_abs_2602_22085
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SocialPulse: On-Device Detection of Social Interactions in Naturalistic Settings Using Smartwatch Multimodal Sensing
Ahmed, Md Sabbir
Petz, Kaitlyn Dorothy
French, Noah
Lakhtakia, Tanvi
Sangani, Aayushi
Rucker, Mark
Chen, Xinyu
Teachman, Bethany A.
Barnes, Laura E.
Human-Computer Interaction
Social interactions are fundamental to well-being, yet automatically detecting them in daily life-particularly using wearables-remains underexplored. Most existing systems are evaluated in controlled settings, focus primarily on in-person interactions, or rely on restrictive assumptions (e.g., requiring multiple speakers within fixed temporal windows), limiting generalizability to real-world use. We present an on-watch interaction detection system designed to capture diverse interactions in naturalistic settings. A core component is a foreground speech detector trained on a public dataset. Evaluated on over 100,000 labeled foreground speech and background sound instances, the detector achieves a balanced accuracy of 85.51%, outperforming prior work by 5.11%. We evaluated the system in a real-world deployment (N=38), with over 900 hours of total smartwatch wear time. The system detected 1,691 interactions, 77.28% were confirmed via participant self-report, with durations ranging from under one minute to over one hour. Among correct detections, 81.45% were in-person, 15.7% virtual, and 1.85% hybrid. We further developed a 15-second window-level audio-only model that enables faster interaction prediction, achieving a balanced accuracy of 90.39% and a sensitivity of 91.01% on 33,698 labeled windows. These results demonstrate the feasibility of real-world interaction sensing and open the door to adaptive, context-aware systems responding to users' dynamic social environments.
title SocialPulse: On-Device Detection of Social Interactions in Naturalistic Settings Using Smartwatch Multimodal Sensing
topic Human-Computer Interaction
url https://arxiv.org/abs/2602.22085