Rare Life Event Detection via Mobile Sensing Using Multi-Task Learning

Arvind Pillai, Subigya Nepal, Andrew Campbell
Proceedings of the Conference on Health, Inference, and Learning, PMLR 209:279-293, 2023.

Abstract

Rare life events significantly impact mental health, and their detection in behavioral studies is a crucial step towards health-based interventions. We envision that mobile sensing data can be used to detect these anomalies. However, the human-centered nature of the problem, combined with the infrequency and uniqueness of these events makes it challenging for unsupervised machine learning methods. In this paper, we first investigate granger-causality between life events and human behavior using sensing data. Next, we propose a multi-task framework with an unsupervised autoencoder to capture irregular behavior, and an auxiliary sequence predictor that identifies transitions in workplace performance to contextualize events. We perform experiments using data from a mobile sensing study comprising N=126 information workers from multiple industries, spanning 10106 days with 198 rare events ($<2%$). Through personalized inference, we detect the exact day of a rare event with an F1 of 0.34, demonstrating that our method outperforms several baselines. Finally, we discuss the implications of our work from the context of real-world deployment.

Cite this Paper

BibTeX
@InProceedings{pmlr-v209-pillai23a, title = {Rare Life Event Detection via Mobile Sensing Using Multi-Task Learning}, author = {Pillai, Arvind and Nepal, Subigya and Campbell, Andrew}, booktitle = {Proceedings of the Conference on Health, Inference, and Learning}, pages = {279--293}, year = {2023}, editor = {Mortazavi, Bobak J. and Sarker, Tasmie and Beam, Andrew and Ho, Joyce C.}, volume = {209}, series = {Proceedings of Machine Learning Research}, month = {22 Jun--24 Jun}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v209/pillai23a/pillai23a.pdf}, url = {https://proceedings.mlr.press/v209/pillai23a.html}, abstract = {Rare life events significantly impact mental health, and their detection in behavioral studies is a crucial step towards health-based interventions. We envision that mobile sensing data can be used to detect these anomalies. However, the human-centered nature of the problem, combined with the infrequency and uniqueness of these events makes it challenging for unsupervised machine learning methods. In this paper, we first investigate granger-causality between life events and human behavior using sensing data. Next, we propose a multi-task framework with an unsupervised autoencoder to capture irregular behavior, and an auxiliary sequence predictor that identifies transitions in workplace performance to contextualize events. We perform experiments using data from a mobile sensing study comprising N=126 information workers from multiple industries, spanning 10106 days with 198 rare events ($<2%$). Through personalized inference, we detect the exact day of a rare event with an F1 of 0.34, demonstrating that our method outperforms several baselines. Finally, we discuss the implications of our work from the context of real-world deployment.} }
Endnote
%0 Conference Paper %T Rare Life Event Detection via Mobile Sensing Using Multi-Task Learning %A Arvind Pillai %A Subigya Nepal %A Andrew Campbell %B Proceedings of the Conference on Health, Inference, and Learning %C Proceedings of Machine Learning Research %D 2023 %E Bobak J. Mortazavi %E Tasmie Sarker %E Andrew Beam %E Joyce C. Ho %F pmlr-v209-pillai23a %I PMLR %P 279--293 %U https://proceedings.mlr.press/v209/pillai23a.html %V 209 %X Rare life events significantly impact mental health, and their detection in behavioral studies is a crucial step towards health-based interventions. We envision that mobile sensing data can be used to detect these anomalies. However, the human-centered nature of the problem, combined with the infrequency and uniqueness of these events makes it challenging for unsupervised machine learning methods. In this paper, we first investigate granger-causality between life events and human behavior using sensing data. Next, we propose a multi-task framework with an unsupervised autoencoder to capture irregular behavior, and an auxiliary sequence predictor that identifies transitions in workplace performance to contextualize events. We perform experiments using data from a mobile sensing study comprising N=126 information workers from multiple industries, spanning 10106 days with 198 rare events ($<2%$). Through personalized inference, we detect the exact day of a rare event with an F1 of 0.34, demonstrating that our method outperforms several baselines. Finally, we discuss the implications of our work from the context of real-world deployment.
APA
Pillai, A., Nepal, S. & Campbell, A.. (2023). Rare Life Event Detection via Mobile Sensing Using Multi-Task Learning. Proceedings of the Conference on Health, Inference, and Learning, in Proceedings of Machine Learning Research 209:279-293 Available from https://proceedings.mlr.press/v209/pillai23a.html.

Related Material