The DOI matches its Crossref record; 43 of the 45 references it cites were found in a registry or an index.
Personalized Multitask Learning for Predicting Tomorrow's Mood, Stress, and Health
Open accessAbstract
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“Our findings also corroborate the results of Taylor et al. (46), who report that personalized Multitask Learning (shared common layers neural network, multi-kernel learning using support vector machines, and hierarchical Bayesian models with a common Dirichlet process prior) improved prediction accuracies by 11–21% over non-personalized models.”
From Personalised depression forecasting using mobile sensor data and ecological momentary assessment (2022) · cites this paper as [46]
In the citing paper
“For instance, StudentLife [63] combined sensing and self-reports to assess the impact of student workload on stress, whereas Snapshot [160] tracked their mood and sleep.”
From Human-centred artificial intelligence for mobile health sensing: challenges and opportunities (2023) · cites this paper as [160]
In the citing paper
“Some recent works employ recurrent neural networks [20], feed-forward layers [159], multi-task learning [160] and autoencoders to fill in missing sensor data [161], or to learn better representations [162].”
From Human-centred artificial intelligence for mobile health sensing: challenges and opportunities (2023) · cites this paper as [160]
In the citing paper
“In addition to group-level fairness, individual fairness arises in several tasks where the target manifests itself differently in distinct (human) subjects. This ranges from the expression of fatigue in runners (54), to stress and emotion in voice (55, 56), and, crucially, mood prediction from wearable sensors (46).”
From Personalised depression forecasting using mobile sensor data and ecological momentary assessment (2022) · cites this paper as [46]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
(2014) · Cited by 33,419
Silhouettes: A graphical aid to the interpretation and validation of cluster analysis
Rousseeuw, P. J. (1987) · Journal of Computational and Applied Mathematics · doi:10.1016/0377-0427(87)90125-7 · Cited by 21,392
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Finn, C., Abbeel, P., & Levine, S. (2017) · arXiv · doi:10.48550/arxiv.1703.03400 · Cited by 8,512
(1999) · Cited by 7,995
Caruana, R. (1997) · Machine Learning · doi:10.1023/a:1007379606734 · Cited by 6,636
DEAP: A Database for Emotion Analysis ;Using Physiological Signals
Koelstra, S., Muhl, C., Soleymani, M., Lee, J.-S., Yazdani, A., Ebrahimi, T., Pun, T., Nijholt, A., & Patras, I. (2012) · IEEE Transactions on Affective Computing · doi:10.1109/t-affc.2011.15 · Cited by 5,093
Psychological Stress and Susceptibility to the Common Cold
Cohen, S., Tyrrell, D. A. J., & Smith, A. P. (1991) · New England Journal of Medicine · doi:10.1056/nejm199108293250903 · Cited by 1,712
Temperament, personality, and the mood and anxiety disorders.
Clark, L. A., Watson, D., & Mineka, S. (1994) · Journal of Abnormal Psychology · doi:10.1037/0021-843x.103.1.103 · Cited by 1,685
Veenhoven, R. (2008) · Journal of Happiness Studies · doi:10.1007/s10902-006-9042-1 · Cited by 771
Research works printed but not linked: 1
- jaques, 2015, Multi-task, multi-kernel learning for estimating individual wellbeing, Proc 28th Int Conf Neural Inf Process Syst Workshop Multimodal ML, 898
Cited by
Sorted by citations
Self-Supervised ECG Representation Learning for Emotion Recognition
Sarkar, P., & Etemad, A. (2020) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2020.3014842 · Cited by 411
Personalized machine learning for robot perception of affect and engagement in autism therapy
Rudovic, O., Lee, J., Dai, M., Schuller, B., & Picard, R. W. (2018) · Science Robotics · doi:10.1126/scirobotics.aao6760 · Cited by 316
Self-citationWearable-Based Affect Recognition—A Review
Schmidt, P., Reiss, A., Dürichen, R., & Laerhoven, K. V. (2019) · Sensors · doi:10.3390/s19194079 · Cited by 292
EntropyHub: An open-source toolkit for entropic time series analysis
Flood, M. W., & Grimm, B. P. (2021) · PLoS ONE · doi:10.1371/journal.pone.0259448 · Cited by 136
Behavioral and Physiological Signals-Based Deep Multimodal Approach for Mobile Emotion Recognition
Yang, K., Wang, C., Gu, Y., Sarsenbayeva, Z., Tag, B., Dingler, T., Wadley, G., & Gonçalves, J. (2021) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2021.3100868 · Cited by 115
Metadata
- Authors
- Taylor, S., Jaques, N., Nosakhare, E., Sano, A., & Picard, R.
- Affiliations
- MIT Media Lab (US)
- Venue
- IEEE Transactions on Affective Computing
- Published
- 2020-04-01
- Volume
- 11
- Issue
- 2
- Pages
- 200-213
- ISSN
- 1949-3045 (ISSN-L)
- 2371-9850
- PMC
- PMC7266106
- OpenAlex
- W2779582454
- Cited by
- 251
- References
- 45
- Citations by year
- 2026: 15 · 2025: 24 · 2024: 37 · 2023: 36 · 2022: 55 · 2021: 30 · 2020: 28
- FWCI
- 18.74
- Type
- journal article
- Language
- en
- Open access
- green
- www.ncbi.nlm.nih.gov
- Licence
- Locations
- IEEE Transactions on Affective Computing (publishedVersion)
- PubMed (publishedVersion)
- PubMed Central (acceptedVersion)
- DSpace@MIT (Massachusetts Institute of Technology) (submittedVersion, cc-by-nc-sa)
- Funders
- MIT Media Lab Consortium
- National Institutes of Health (R01GM105018)
- Samsung
- NEC Corporation
- Natural Sciences and Engineering Research Council of Canada
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Emotion and Mood Recognition
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Mental Health Research Topics
- Keywords
- mood prediction, stress prediction, health prediction, multi-task learning, personalized machine learning, individual differences, Bayesian hierarchical model, Dirichlet process, wearable sensors, meteorological observations, well-being
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
