Predicting students' happiness from physiology, phone, mobility, and behavioral data
Open accessThe DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.
Abstract
In order to model students' happiness, we apply machine learning methods to data collected from undergrad students monitored over the course of one month each. The data collected include physiological signals, location, smartphone logs, and survey responses to behavioral questions. Each day, participants reported their wellbeing on measures including stress, health, and happiness. Because of the relationship between happiness and depression, modeling happiness may help us to detect individuals who are at risk of depression and guide interventions to help them. We are also interested in how behavioral factors (such as sleep and social activity) affect happiness positively and negatively. A variety of machine learning and feature selection techniques are compared, including Gaussian Mixture Models and ensemble classification. We achieve 70% classification accuracy of self-reported happiness on held-out test data.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
Stress, social support, and the buffering hypothesis
Cohen, S., & Wills, T. A. (1985) · Psychological Bulletin · doi:10.1037/0033-2909.98.2.310 · Cited by 18,093 · cited 1×
“Social support has been shown to mediate stress [7], protect against depression [8], and even improve overall health and recovery from illness [9].”
BackgroundCaruana, R. (1997) · Machine Learning · doi:10.1023/a:1007379606734 · Cited by 6,636
Flourish: A Visionary New Understanding of Happiness and Well-Being
(2011) · Choice Reviews Online · doi:10.5860/choice.48-7217 · Cited by 5,543 · cited 3×
“…and low stress state could be indicative of depression (sadness and apathy), whereas a high happiness high stress state could actually represent greater underlying wellbeing than a non-stressed state, given the contribution of personal achievement and engagement with work to overall wellbeing [4].”
BackgroundLoneliness matters: a theoretical and empirical review of consequences and mechanisms
Hawkley, L. C., & Cacioppo, J. T. (2010) · Annals of Behavioral Medicine · doi:10.1007/s12160-010-9210-8 · Cited by 4,782
A survey of mobile phone sensing
Lane, N., Miluzzo, E., Lu, H., Peebles, D., Choudhury, T., & Campbell, A. (2010) · IEEE Communications Magazine · doi:10.1109/mcom.2010.5560598 · Cited by 2,292
Tsuno, N., Besset, A., & Ritchie, K. (2005) · The Journal of Clinical Psychiatry · doi:10.4088/jcp.v66n1008 · Cited by 1,084
Bright light resets the human circadian pacemaker independent of the timing of the sleep-wake cycle
Czeisler, C. A., Allan, J. S., Strogatz, S. H., Ronda, J. M., Sánchez, R., Ríos, C. D., Freitag, W. O., Richardson, G. S., & Kronauer, R. E. (1986) · Science · doi:10.1126/science.3726555 · Cited by 770 · cited 2×
“Further, simply using the phone itself may affect wellbeing through sleep quality; the phone screen emits a large amount of artificial light, which has been shown to adversely affect the circadian rhythm and sleep [12].”
BackgroundA Wearable Sensor for Unobtrusive, Long-Term Assessment of Electrodermal Activity
Poh, M.-Z., Swenson, N. C., & Picard, R. W. (2010) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2009.2038487 · Cited by 693 · cited 1×
“EDA measures sudo-motor innervation and sweat gland activity, which is increased through activity of the sympathetic nervous system (SNS) [25].”
BackgroundSelf-citationStress Recognition Using Wearable Sensors and Mobile Phones
Sano, A., & Picard, R. W. (2013) · 2013 Humaine Association Conference on Affective Computing and Intelligent Interaction · doi:10.1109/acii.2013.117 · Cited by 523
Self-citationKisch, J., Leino, E. V., & Silverman, M. M. (2005) · Suicide and Life-Threatening Behavior · doi:10.1521/suli.35.1.3.59263 · Cited by 489 · cited 1×
“Addressing depression among college students has become a major concern for some universities, especially given the fact that 18-24-year-olds have the highest incidence of suicidal ideation, and suicide has become the third leading cause of death among college-aged individuals [3].”
BackgroundMoodScope: building a mood sensor from smartphone usage patterns
LiKamWa, R., Liu, Y., Lane, N. D., & Zhong, L. (2013) · Proceeding of the 11th annual international conference on Mobile systems, applications, and services · doi:10.1145/2462456.2464449 · Cited by 444 · cited 1×
“There have been preliminary studies demonstrating that mood can be classified using smartphone data [17] [19], and Bogomolov and colleagues”
BackgroundPersonality, self-esteem, and demographic predictions of happiness and depression
Cheng, H., & Furnham, A. (2003) · Personality and Individual Differences · doi:10.1016/s0191-8869(02)00078-8 · Cited by 413
Ivon, A., Cooper David, G., Winslow, B., Park, W. B., Kasia, M., & Robert, C. (2009) · Frontiers in Artificial Intelligence and Applications · doi:10.3233/978-1-60750-028-5-17 · Cited by 382 · cited 1×
“Physiological measures such as electrodermal activity (EDA) are also frequently used in studies related to affect and wellbeing (e.g. [ 21], [22], [23], [24]).”
MethodAutomatic identification of artifacts in electrodermal activity data
Taylor, S., Jaques, N., Chen, W., Fedor, S., Sano, A., & Picard, R. (2015) · 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2015.7318762 · Cited by 279 · cited 1×
“recording artifacts we applied an algorithm described in [31], 02:22:24 02:22:54 02:23:24 02:23:54 02:24:24”
Self-citationDaily Stress Recognition from Mobile Phone Data, Weather Conditions and Individual Traits
Bogomolov, A., Lepri, B., Ferron, M., Pianesi, F., & Pentland, A. (. (2014) · Proceedings of the 22nd ACM international conference on Multimedia · doi:10.1145/2647868.2654933 · Cited by 217
Can smartphones detect stress-related changes in the behaviour of individuals?
Bauer, G., & Lukowicz, P. (2012) · 2012 IEEE International Conference on Pervasive Computing and Communications Workshops · doi:10.1109/percomw.2012.6197525 · Cited by 111 · cited 3×
“Predicting stress from smartphone logs has been attempted by multiple researchers (e.g. [ 16] [17] [18]).”
BackgroundMethodHappiness Recognition from Mobile Phone Data
Bogomolov, A., Lepri, B., & Pianesi, F. (2013) · 2013 International Conference on Social Computing · doi:10.1109/socialcom.2013.118 · Cited by 67 · cited 1×
“There have been prelimi-nary studies demonstrating that mood can be classified using smartphone data [17] [19], and Bogomolov and colleagues have successfully predicted happiness from a combination of smartphone data, personality, and weather patterns [20].”
BackgroundSano, A., & Picard, R. W. (2014) · 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society · doi:10.1109/embc.2014.6943744 · Cited by 25 · cited 2×
“Other research has investigated the link between EDA and sleep quality [26] [27].”
BackgroundSelf-citationRecognition of sleep dependent memory consolidation with multi-modal sensor data
Sano, A., & Picard, R. W. (2013) · 2013 IEEE International Conference on Body Sensor Networks · doi:10.1109/bsn.2013.6575479 · Cited by 12
Self-citation
Cited by
Sano, A., Taylor, S., McHill, A. W., Phillips, A. J., Barger, L. K., Klerman, E., & Picard, R. (2018) · Journal of Medical Internet Research · doi:10.2196/jmir.9410 · Cited by 333
“Additionally, because our population spent most of their time on campus or at their residence, we computed whether the day’s mobility pattern varied from the typical routine based on a Gaussian mixture model trained for each participant’s 1-month mobility patterns [49].”
MethodSelf-citationPersonalized Multitask Learning for Predicting Tomorrow's Mood, Stress, and Health
Taylor, S., Jaques, N., Nosakhare, E., Sano, A., & Picard, R. (2020) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2017.2784832 · Cited by 251
“These scores represent state-of-the-art performance on this dataset, sur-passing prior published work by 5-13 percent prediction accuracy [9], [10].”
BackgroundMethodResultInfluentialSelf-citationRohani, D. A., Faurholt-Jepsen, M., Kessing, L. V., & Bardram, J. E. (2017) · doi:10.2196/preprints.9691 · Cited by 195
“For instance, studies assessing “happiness,” “well-being,” and “quality of life” have been excluded in this review [29-33], even though it has been shown that happiness scores correlated moderately with depression, measured using BDI (r=−0.”
BackgroundResultDeepMood: Forecasting Depressed Mood Based on Self-Reported Histories via Recurrent Neural Networks
Suhara, Y., Xu, Y., & Pentland, A. '. (2017) · Proceedings of the 26th International Conference on World Wide Web · doi:10.1145/3038912.3052676 · Cited by 163
“We used SVM as a baseline learning algorithm because it has been used in previous studies for mood prediction [6][16][38].”
BackgroundMethodEMMA: an emotion-aware wellbeing chatbot
Ghandeharioun, A., McDuff, D., Czerwinski, M., & Rowan, K. (2019) · 2019 8th International Conference on Affective Computing and Intelligent Interaction (ACII) · doi:10.1109/acii.2019.8925455 · Cited by 126
“Examples include using smartphone data to model social interactions [14], to study the relationship between mood and sleep [15], to detect stress, happiness, and mood [10], [16]–[20], and to predict depressive symptoms [21].”
BackgroundSelf-citation
Metadata
- Authors
- Jaques, N., Taylor, S., Azaria, A., Ghandeharioun, A., Sano, A., & Picard, R.
- Venue
- 2015 International Conference on Affective Computing and Intelligent Interaction (ACII)
- Publisher
- IEEE
- Published
- 2015-09
- Volume
- 2015
- Pages
- 222-228
- OpenAlex
- W2189564841
- Cited by
- 137
- References
- 19
- FWCI
- 12.95
- Type
- conference paper
- Language
- en
- Open access
- green
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.