Display options
Share it on

Proc ACM Interact Mob Wearable Ubiquitous Technol. 2020 Dec;4(4). doi: 10.1145/3432210.

Automated Detection of Stressful Conversations Using Wearable Physiological and Inertial Sensors.

Proceedings of the ACM on interactive, mobile, wearable and ubiquitous technologies

Rummana Bari, Md Mahbubur Rahman, Nazir Saleheen, Megan Battles Parsons, Eugene H Buder, Santosh Kumar

Affiliations

  1. University of Memphis, Electrical and Computer Engineering, Memphis, TN, 38152, USA.
  2. University of Memphis, Computer Science, Memphis, TN, USA.
  3. University of Memphis, Communication Science and Disorder, Memphis, TN, USA.

PMID: 34099995 PMCID: PMC8180313 DOI: 10.1145/3432210

Abstract

Stressful conversation is a frequently occurring stressor in our daily life. Stressors not only adversely affect our physical and mental health but also our relationships with family, friends, and coworkers. In this paper, we present a model to automatically detect stressful conversations using wearable physiological and inertial sensors. We conducted a lab and a field study with cohabiting couples to collect ecologically valid sensor data with temporally-precise labels of stressors. We introduce the concept of stress cycles, i.e., the physiological arousal and recovery, within a stress event. We identify several novel features from stress cycles and show that they exhibit distinguishing patterns during stressful conversations when compared to physiological response due to other stressors. We observe that hand gestures also show a distinct pattern when stress occurs due to stressful conversations. We train and test our model using field data collected from 38 participants. Our model can determine whether a detected stress event is due to a stressful conversation with an F1-score of 0.83, using features obtained from only one stress cycle, facilitating intervention delivery within 3.9 minutes since the start of a stressful conversation.

References

  1. Biol Psychol. 1996 Jan 5;42(1-2):147-64 - PubMed
  2. Sensors (Basel). 2019 Apr 18;19(8): - PubMed
  3. Sensors (Basel). 2018 Jul 31;18(8): - PubMed
  4. J Pers Soc Psychol. 2006 Apr;90(4):613-28 - PubMed
  5. ACM BCB. 2014;2014:479-488 - PubMed
  6. Proc ACM Int Conf Ubiquitous Comput. 2015 Sep;2015:493-504 - PubMed
  7. Age Ageing. 1997 Jan;26(1):15-9 - PubMed
  8. Bionanoscience. 2013;3:172-183 - PubMed
  9. IEEE Trans Inf Technol Biomed. 2012 Mar;16(2):279-86 - PubMed
  10. Assessment. 2002 Mar;9(1):41-55 - PubMed
  11. Psychosom Med. 2009 Apr;71(3):329-33 - PubMed
  12. Psychosom Med. 1993 Jul-Aug;55(4):347-63 - PubMed
  13. J Pers Soc Psychol. 1998 Sep;75(3):670-80 - PubMed
  14. Psychosom Med. 2012 May;74(4):398-409 - PubMed
  15. Annu Int Conf IEEE Eng Med Biol Soc. 2016 Aug;2016:173-176 - PubMed
  16. Neurosci Biobehav Rev. 2010 Sep;35(1):2-16 - PubMed
  17. PLoS One. 2019 Jul 26;14(7):e0218429 - PubMed
  18. J Genet Couns. 2011 Jun;20(3):270-86 - PubMed
  19. Proc Int Conf Automot User Interfaces Interact Veh Appl (2014). 2014 Sep 17;2014: - PubMed
  20. Psychoneuroendocrinology. 2018 Jul;93:107-116 - PubMed
  21. Eur J Appl Physiol. 2011 Jul;111(7):1497-505 - PubMed
  22. Psychophysiology. 1997 May;34(3):266-75 - PubMed
  23. Neurosci Biobehav Rev. 2010 Sep;35(1):33-8 - PubMed
  24. Proc SIGCHI Conf Hum Factor Comput Syst. 2016 May;2016:4489-4501 - PubMed
  25. Proc ACM Interact Mob Wearable Ubiquitous Technol. 2018 Mar;2(1): - PubMed
  26. Proc ACM Int Conf Ubiquitous Comput. 2015 Sep;2015:505-516 - PubMed
  27. Science. 2004 Dec 3;306(5702):1776-80 - PubMed

Publication Types

Grant support