Having a Bad Day? Detecting the Impact of Atypical Life Events Using Wearable Sensors

Life events can dramatically affect our psychological state and work performance. Stress, for example, has been linked to professional dissatisfaction, increased anxiety, and workplace burnout. We explore the impact of positive and negative life events on a number of psychological constructs through a multi-month longitudinal study of hospital and aerospace workers. Through causal inference, we demonstrate that positive life events increase positive affect, while negative events increase stress, anxiety and negative affect. While most events have a transient effect on psychological states, major negative events, like illness or attending a funeral, can reduce positive affect for multiple days. Next, we assess whether these events can be detected through wearable sensors, which can cheaply and unobtrusively monitor health-related factors. We show that these sensors paired with embedding-based learning models can be used ``in the wild'' to capture atypical life events in hundreds of workers across both datasets. Overall our results suggest that automated interventions based on physiological sensing may be feasible to help workers regulate the negative effects of life events.

[1]  Cem Ersoy,et al.  Continuous Stress Detection Using Wearable Sensors in Real Life: Algorithmic Programming Contest Case Study , 2019, Sensors.

[2]  Elena Smets,et al.  Large-scale wearable data reveal digital phenotypes for daily-life stress detection , 2018, npj Digital Medicine.

[3]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.

[4]  David Ellis,et al.  Stress Detection Using Wearable Physiological and Sociometric Sensors , 2017, Int. J. Neural Syst..

[5]  Kasper Hornbæk,et al.  An affect detection technique using mobile commodity sensors in the wild , 2016, UbiComp.

[6]  Sheldon Cohen,et al.  Psychological stress and disease. , 2007, JAMA.

[7]  Shrikanth Narayanan,et al.  TILES-2018, a longitudinal physiologic and behavioral data set of hospital workers , 2020, Scientific data.

[8]  Joel E Dimsdale,et al.  Psychological stress and cardiovascular disease. , 2008, Journal of the American College of Cardiology.

[9]  Yu Huang,et al.  Discovery of Behavioral Markers of Social Anxiety from Smartphone Sensor Data , 2017, DigitalBioMarker@MobiSys.

[10]  G. Zielhuis,et al.  The effect of anxiety and depression on the outcome of in-vitro fertilization. , 2001, Human reproduction.

[11]  Akane Sano,et al.  Predicting Tomorrow's Mood, Health, and Stress Level using Personalized Multitask Learning and Domain Adaptation , 2017, AffComp@IJCAI.

[12]  P. Burnard,et al.  A longitudinal study of stress and self-esteem in student nurses. , 2010, Nurse education today.

[13]  Pierre Geurts,et al.  Extremely randomized trees , 2006, Machine Learning.

[14]  O. Aasland,et al.  Development of the Alcohol Use Disorders Identification Test (AUDIT): WHO Collaborative Project on Early Detection of Persons with Harmful Alcohol Consumption--II. , 1993, Addiction.

[15]  Shrikanth Narayanan,et al.  Estimating Individualized Daily Self-Reported Affect with Wearable Sensors , 2019, 2019 IEEE International Conference on Healthcare Informatics (ICHI).

[16]  Akane Sano,et al.  Recognizing academic performance, sleep quality, stress level, and mental health using personality traits, wearable sensors and mobile phones , 2015, 2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks (BSN).

[17]  Michael I. Jordan,et al.  JOINT MODELING OF MULTIPLE TIME SERIES VIA THE BETA PROCESS WITH APPLICATION TO MOTION CAPTURE SEGMENTATION , 2013, 1308.4747.

[18]  Muhammad Ismail Ramay,et al.  Impact of Stress on Employees Job Performance: A Study on Banking Sector of Pakistan , 2010 .

[19]  Chak Fu Lam,et al.  Too much of a good thing: Curvilinear effect of positive affect on proactive behaviors , 2014 .

[20]  Jennifer Healey,et al.  Detecting stress during real-world driving tasks using physiological sensors , 2005, IEEE Transactions on Intelligent Transportation Systems.

[21]  Hal R Varian,et al.  Causal inference in economics and marketing , 2016, Proceedings of the National Academy of Sciences.

[22]  V. Nam Global Adult Tobacco Survey (GATS) , 2010 .

[23]  E. Guthrie,et al.  Psychological stress and burnout in medical students: a five-year prospective longitudinal study , 1998, Journal of the Royal Society of Medicine.

[24]  Begoña García Zapirain,et al.  A Stress Sensor Based on Galvanic Skin Response (GSR) Controlled by ZigBee , 2012, Sensors.

[25]  David Ellis,et al.  Stress Detection Using Wearable Physiological Sensors , 2015, IWINAC.

[26]  Ryan L. Boyd,et al.  The Development and Psychometric Properties of LIWC2015 , 2015 .

[27]  K. Vohs,et al.  Case Western Reserve University , 1990 .

[28]  Sinan Aral,et al.  Exercise contagion in a global social network , 2017, Nature Communications.

[29]  Mirco Musolesi,et al.  Trajectories of depression: unobtrusive monitoring of depressive states by means of smartphone mobility traces analysis , 2015, UbiComp.

[30]  Sebastian Ruder,et al.  An Overview of Multi-Task Learning in Deep Neural Networks , 2017, ArXiv.

[31]  O. V. Ramana Murthy,et al.  Stress Detection in Working People , 2017 .

[32]  H. Christensen,et al.  A short form of the Positive and Negative Affect Schedule: evaluation of factorial validity and invariance across demographic variables in a community sample , 1999 .

[33]  Amy Loutfi,et al.  Data Mining for Wearable Sensors in Health Monitoring Systems: A Review of Recent Trends and Challenges , 2013, Sensors.

[34]  Matjaz Gams,et al.  Monitoring stress with a wrist device using context , 2017, J. Biomed. Informatics.

[35]  P. Fernández-Berrocal,et al.  Emotional intelligence and acute pain: the mediating effect of negative affect. , 2011, The journal of pain : official journal of the American Pain Society.

[36]  Shrikanth Narayanan,et al.  Learning Behavioral Representations from Wearable Sensors , 2020, SBP-BRiMS.

[37]  Eric Gilbert,et al.  VADER: A Parsimonious Rule-Based Model for Sentiment Analysis of Social Media Text , 2014, ICWSM.

[38]  Daniel J Buysse,et al.  The Pittsburgh sleep quality index: A new instrument for psychiatric practice and research , 1989, Psychiatry Research.

[39]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[40]  Alex Pentland,et al.  Reality mining: sensing complex social systems , 2006, Personal and Ubiquitous Computing.

[41]  A. Anderson,et al.  Positive affect increases the breadth of attentional selection , 2007, Proceedings of the National Academy of Sciences.

[42]  S. Parker,et al.  A new model of work role performance: Positive behavior in uncertain and interdependent contexts , 2007 .

[43]  J. Molson,et al.  Job Stress, Job Performance and Organizational Commitment in a Multinational Company: An Empirical Study in two Countries , 2011 .

[44]  Emre Ertin,et al.  cStress: towards a gold standard for continuous stress assessment in the mobile environment , 2015, UbiComp.

[45]  Antonio Torralba,et al.  Depth Estimation from Image Structure , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[46]  D. Cox The Regression Analysis of Binary Sequences , 1958 .

[47]  Javad Frounchi,et al.  Machine learning-based signal processing using physiological signals for stress detection , 2015, 2015 22nd Iranian Conference on Biomedical Engineering (ICBME).

[48]  John Ifcher,et al.  Happiness and Time Preference: The Effect of Positive Affect in a Random-Assignment Experiment , 2011 .

[49]  István Vassányi,et al.  Stress Detection Using Low Cost Heart Rate Sensors , 2016, Journal of healthcare engineering.

[50]  Geoffrey E. Hinton Connectionist Learning Procedures , 1989, Artif. Intell..

[51]  Alex Pentland,et al.  Daily Stress Recognition from Mobile Phone Data, Weather Conditions and Individual Traits , 2014, ACM Multimedia.

[52]  S. Gosling,et al.  A very brief measure of the Big-Five personality domains , 2003 .

[53]  Fanglin Chen,et al.  StudentLife: assessing mental health, academic performance and behavioral trends of college students using smartphones , 2014, UbiComp.

[54]  R. Goetzel,et al.  Ten modifiable health risk factors are linked to more than one-fifth of employer-employee health care spending. , 2012, Health affairs.