Eustress or distress: an empirical study of perceived stress in everyday college life

Eustress is literally the "good stress" that associated with positive feelings and health benefits. Previous studies focused on general stress, where the concept of eustress has been overlooked. This paper presents a novel approach towards stress recognition using data collected from wearable sensors, smartphones, and computers. The main goal is to determine if behavioral factors can help differentiate eustress from another kind of stress. We conducted a natural experiment to collect user smartphone and computer usage, heart rate and survey data in situ. By correlation and principle component analysis, a set of features could then be constructed. The performance was evaluated under leave-one-subject-out cross-validation, where the combined behavioral and physiological features enabled us to achieve 84.85% accuracy for general stress, 71.33% one kind of eustress as an urge for better performance, and 57.34% for eustress as a state of better mood. This work provided an encouraging result as an initial study for measuring eustress.

[1]  N. Meiran,et al.  Component Processes in Task Switching , 2000, Cognitive Psychology.

[2]  Yalcin Isler,et al.  Combining classical HRV indices with wavelet entropy measures improves to performance in diagnosing congestive heart failure , 2007, Comput. Biol. Medicine.

[3]  Joseph E. Mietus,et al.  Time Domain Measures: From Variance to pNNx , 2006 .

[4]  H. Selye,et al.  [Stress without distress]. , 1976, Bruxelles medical.

[5]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[6]  R. Lazarus.  From psychological stress to the emotions: a history of changing outlooks. , 1993, Annual review of psychology.

[7]  M. Sholokhov.  The Eustress Concept : Problems and Outlooks , 2014 .

[8]  Tamás D. Gedeon,et al.  Objective measures, sensors and computational techniques for stress recognition and classification: A survey , 2012, Comput. Methods Programs Biomed..

[9]  Akane Sano,et al.  Stress Recognition Using Wearable Sensors and Mobile Phones , 2013, 2013 Humaine Association Conference on Affective Computing and Intelligent Interaction.

[10]  H. Benson,et al.  How much stress is too much? , 1980, Harvard business review.

[11]  Martin L. Griss,et al.  Activity-Aware Mental Stress Detection Using Physiological Sensors , 2010, MobiCASE.

[12]  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).

[13]  H Selye,et al.  The Stress Syndrome , 1965, [Kango gijutsu] : [Nursing technique].