Show simple item record

dc.contributor.authorTaylor, Sara Ann
dc.contributor.authorJaques, Natasha Mary
dc.contributor.authorNosakhare, Ehimwenma
dc.contributor.authorSano, Akane
dc.contributor.authorPicard, Rosalind W.
dc.date.accessioned2022-07-15T15:56:34Z
dc.date.available2021-10-27T19:57:33Z
dc.date.available2022-07-15T15:56:34Z
dc.date.issued2020
dc.identifier.urihttps://hdl.handle.net/1721.1/133994.2
dc.description.abstract© 2010-2012 IEEE. While accurately predicting mood and wellbeing could have a number of important clinical benefits, traditional machine learning (ML) methods frequently yield low performance in this domain. We posit that this is because a one-size-fits-all machine learning model is inherently ill-suited to predicting outcomes like mood and stress, which vary greatly due to individual differences. Therefore, we employ Multitask Learning (MTL) techniques to train personalized ML models which are customized to the needs of each individual, but still leverage data from across the population. Three formulations of MTL are compared: i) MTL deep neural networks, which share several hidden layers but have final layers unique to each task; ii) Multi-task Multi-Kernel learning, which feeds information across tasks through kernel weights on feature types; and iii) a Hierarchical Bayesian model in which tasks share a common Dirichlet Process prior. We offer the code for this work in open source. These techniques are investigated in the context of predicting future mood, stress, and health using data collected from surveys, wearable sensors, smartphone logs, and the weather. Empirical results demonstrate that using MTL to account for individual differences provides large performance improvements over traditional machine learning methods and provides personalized, actionable insights.en_US
dc.language.isoen
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en_US
dc.relation.isversionof10.1109/TAFFC.2017.2784832en_US
dc.rightsCreative Commons Attribution-Noncommercial-Share Alikeen_US
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/4.0/en_US
dc.sourceMIT web domainen_US
dc.titlePersonalized Multitask Learning for Predicting Tomorrow's Mood, Stress, and Healthen_US
dc.typeArticleen_US
dc.contributor.departmentMassachusetts Institute of Technology. Media Laboratoryen_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Scienceen_US
dc.relation.journalIEEE Transactions on Affective Computingen_US
dc.eprint.versionAuthor's final manuscripten_US
dc.type.urihttp://purl.org/eprint/type/JournalArticleen_US
eprint.statushttp://purl.org/eprint/status/PeerRevieweden_US
dc.date.updated2019-07-31T16:49:32Z
dspace.orderedauthorsTaylor, S; Jaques, N; Nosakhare, E; Sano, A; Picard, Ren_US
dspace.date.submission2019-07-31T16:49:34Z
mit.journal.volume11en_US
mit.journal.issue2en_US
mit.metadata.statusPublication Information Neededen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

VersionItemDateSummary

*Selected version