Abstract
As smart speakers become increasingly integrated into everyday home life, there is growing interest in leveraging these speakers to proactively deliver personalized proactive services. To enhance user experience and engagement of proactive services, a key challenge is identifying opportune moments, user contexts when users are most interruptible to engage in proactive services. Researchers have identified such moments by exploring interruptibility across various user contexts (in which contexts users are more interruptible), and several datasets have been released with interruptibility labels. However, no publicly available dataset has focused specifically on interruptibility within home environments. To fill this gap, we present INPROSH, a dataset collected from 26 participants over a three-week in-the-wild field study. Participants used proactive services via smart speakers in their homes. INPROSH comprises 2,830 cases, each annotated with interruptibility labels and enriched with contextual information, including temporal, spatial, and behavioral contexts, as well as surrounding image and sound recordings near the smart speakers. We believe INPROSH will support a deeper understanding and more accurate detection of interruptibility in home environments.
Subjects
Acknowledgements
This work was supported by the Institute of Information & Communications Technology Planning & Evaluation(IITP) grant funded by the Korea government(MSIT)(IITP-2026-RS-2023-00260267) and the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIT)(RS-2023-00242528). We gratefully acknowledge Jiwook Lee and Minyeong Kim for their invaluable contributions and active involvement in the experimental procedures and data collection.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/
About this article
Cite this article
Sunatullaev, G., Hwang, J., Lee, J. et al. Multimodal-context Interruptibility Dataset for Proactive Services on Smart Speakers at Home. Sci Data (2026). https://doi.org/10.1038/s41597-026-07618-0
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41597-026-07618-0
Facts Only
* The study involved 26 participants over a three-week in-the-wild field study.
* Participants used proactive services via smart speakers in their homes.
* INPROSH comprises 2,830 cases.
* Each case is annotated with interruptibility labels.
* Data includes temporal, spatial, and behavioral contexts.
* The dataset includes surrounding image and sound recordings near the smart speakers.
* The work was supported by grants from IITP and NRF.
Executive Summary
Full Take
The focus on interruptibility within domestic environments shifts the focus of proactive service research from general user context to highly specific, situated behavioral dynamics. The creation of INPROSH moves the field toward empirical measurement of real-world interaction friction, which is crucial for developing genuinely helpful proactive systems rather than simply optimizing for theoretical contexts. A key implication is that the success of smart home integration depends not only on the accuracy of prediction but also on the system's sensitivity to nuanced, dynamic human interruption patterns specific to living spaces. The pattern suggests a necessary shift from abstract interruptibility metrics to embodied, multi-modal context capture in future Human-Computer Interaction (HCI) research.
What further contextual factors are missing that might influence interruptibility beyond temporal, spatial, and behavioral data? How does the study's focus on 'in-the-wild' setting limit the generalizability of the derived interruptibility models across different household structures or occupancy patterns? What mechanisms exist for the proactive system to adapt its timing based on detected real-time emotional states inferred from the ambient recordings rather than solely on explicit behavioral labels?
Sentinel — Human
The text exhibits the formal, precise structure of scholarly research reporting, strongly suggesting it is a human-authored abstract or introductory section from a scientific publication.