ABSTRACT
Studies have shown that drivers’ emotions can be assessed via changes in their physiology and facial behaviour. This study examined this approach as a means of gauging user experience (UX) in an automotive user study. 36 drivers’ responses to typical UX-style questions were compared with computational estimates of their emotional state, based on changes in their cardiac, respiratory, electrodermal and facial signals. The drivers’ arousal and valence levels were monitored in real-time as they drove a 23-mile route around Sunnyvale, CA. These estimates corresponded with two independent observers’ judgments of the drivers’ emotions. The results highlighted a disparity between the self-report and algorithmic scores—the drivers who answered the UX questions more positively experienced higher levels of stress—evidenced by higher arousal and lower valence algorithmic scores. The findings highlight the value of supplementing self-report measures with objective estimates of drivers’ emotions in automotive UX research.
- Lisa Feldman Barrett, Ralph Adolphs, Stacy Marsella, Aleix M Martinez, and Seth D Pollak. 2019. Emotional expressions reconsidered: challenges to inferring emotion from human facial movements. Psychological Science in the Public Interest 20, 1 (2019), 1–68.Google ScholarCross Ref
- Michael Braun, Florian Weber, and Florian Alt. 2020. Affective Automotive User Interfaces – Reviewing the State of Emotion Regulation in the Car. arXiv preprint arXiv:2003.13731 (03 2020).Google Scholar
- Hua Cai and Yingzi Lin. 2011. Modeling of operators’ emotion and task performance in a virtual driving environment. International Journal of Human-Computer Studies 69, 9 (2011), 571–586.Google ScholarDigital Library
- Stefano Coretta. 2020. tidymv: Tidy Model Visualisation for Generalised Additive Models. https://CRAN.R-project.org/package=tidymv R package version 3.0.0.Google Scholar
- Joseph F Coughlin, Bryan Reimer, and Bruce Mehler. 2011. Monitoring, managing, and motivating driver safety and well-being. IEEE Pervasive Computing 10, 3 (2011), 14–21.Google ScholarDigital Library
- Na Du, Feng Zhou, Elizabeth M. Pulver, Dawn M. Tilbury, Lionel P. Robert, Anuj K. Pradhan, and X. Jessie Yang. 2020. Examining the effects of emotional valence and arousal on takeover performance in conditionally automated driving. Transportation Research Part C: Emerging Technologies 112 (2020), 78 – 87. https://doi.org/10.1016/j.trc.2020.01.006Google ScholarCross Ref
- Stephen H Fairclough, Marjolein van der Zwaag, Elena Spiridon, and Joyce Westerink. 2014. Effects of mood induction via music on cardiovascular measures of negative emotion during simulated driving. Physiology & behavior 129 (2014), 173–180.Google Scholar
- Susan Folkman. 2013. Stress: Appraisal and Coping. Springer New York, New York, NY, 1913–1915. https://doi.org/10.1007/978-1-4419-1005-9_215Google Scholar
- Hua Gao, Anil Yüce, and Jean-Philippe Thiran. 2014. Detecting emotional stress from facial expressions for driving safety. In 2014 IEEE International Conference on Image Processing (ICIP). IEEE, 5961–5965.Google ScholarCross Ref
- G Giannakakis, Matthew Pediaditis, Dimitris Manousos, Eleni Kazantzaki, Franco Chiarugi, Panagiotis G Simos, Kostas Marias, and Manolis Tsiknakis. 2017. Stress and anxiety detection using facial cues from videos. Biomedical Signal Processing and Control 31 (2017), 89–101.Google ScholarCross Ref
- Sylvia D Kreibig. 2010. Autonomic nervous system activity in emotion: A review. Biological psychology 84, 3 (2010), 394–421.Google Scholar
- Yuri Masaoka and Ikuo Homma. 1997. Anxiety and respiratory patterns: their relationship during mental stress and physical load. International Journal of Psychophysiology 27, 2 (1997), 153–159.Google ScholarCross Ref
- Bruce Mehler, Bryan Reimer, and Joseph F. Coughlin. 2010. Physiological Reactivity to Graded Levels of Cognitive Workload across Three Age Groups: An On-Road Evaluation. Proceedings of the Human Factors and Ergonomics Society Annual Meeting 54, 24 (2010), 2062–2066. https://doi.org/10.1177/154193121005402409Google ScholarCross Ref
- Yoko Nagai, Christopher Iain Jones, and Arjune Sen. 2019. Galvanic skin response (gsr)/electrodermal/skin conductance biofeedback on epilepsy: a systematic review and meta-analysis. Frontiers in neurology 10 (2019), 377.Google Scholar
- Delroy L Paulhus. 1984. Two-component models of socially desirable responding.Journal of personality and social psychology 46, 3(1984), 598.Google Scholar
- R Core Team. 2020. R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna, Austria. https://www.R-project.org/Google Scholar
- Ernst Roidl, Berit Frehse, and Rainer Höger. 2014. Emotional states of drivers and the impact on speed, acceleration and traffic violations—A simulator study. Accident Analysis & Prevention 70 (2014), 282–292.Google ScholarCross Ref
- James A Russell. 1980. A circumplex model of affect.Journal of personality and social psychology 39, 6(1980), 1161.Google Scholar
- H. Sawai, G. Inou, and E. Koyama. 2015. Evaluating Optimal Arousal Level during the Task Based on Performance and Positive Mood: Extracting Indices Reflecting the Relationship among Arousal, Performance, and Mood. In 2015 3rd International Conference on Applied Computing and Information Technology/2nd International Conference on Computational Science and Intelligence. 213–218.Google Scholar
- Sensum. 2020. Sensum Empathic AI Developer Kit. https://sensum.co/.Google Scholar
- SHORE. 2020. Emotion Recognition Software SHORE®: Fast, Reliable and Real-time Capable. http://www.iis.fraunhofer.de/shore.Google Scholar
- Christine Spencer, Ibrahim A Koc, Chihiro Suga, Alex Lee, Anupama M Dhareshwar, Elin Franzén, Maria Iozzo, Gawain Morrison, and Gary J McKeown. 2020. A Comparison of Unimodal and Multimodal Measurements of Driver Stress in Real-World Driving Conditions. https://doi.org/10.31234/osf.io/en5r3Google Scholar
- Christine Spencer, Daniel Moore, Gary McKeown, Lucy Rutherford, and Gawain Morrison. 2019. Context matters: protocol ordering effects on physiological arousal and experienced stress during a simulated driving task. In 2019 8th International Conference on Affective Computing and Intelligent Interaction (ACII). IEEE, Association for Computing Machinery, Cambridge, UK, 1–7.Google ScholarCross Ref
- Fabius Steinberger, Ronald Schroeter, and Diana Babiac. 2017. Engaged Drivers - Safe Drivers: Gathering Real-Time Data from Mobile and Wearable Devices for Safe-Driving Apps. In Automotive user interfaces. Springer.Google Scholar
- Lana Trick, Seneca Brandigampola, and James Enns. 2012. How fleeting emotions affect hazard perception and steering while driving: The impact of image arousal and valence. Accident; analysis and prevention 45 (03 2012), 222–9. https://doi.org/10.1016/j.aap.2011.07.006Google Scholar
- Elke Vlemincx, Joachim Taelman, Steven De Peuter, Ilse Van Diest, and Omer Van Den Bergh. 2011. Sigh rate and respiratory variability during mental load and sustained attention. Psychophysiology 48, 1 (2011), 117–120.Google ScholarCross Ref
- Hadley Wickham. 2016. ggplot2: Elegant Graphics for Data Analysis. Springer-Verlag New York. https://ggplot2.tidyverse.orgGoogle Scholar
- Simon N Wood. 2011. Fast stable restricted maximum likelihood and marginal likelihood estimation of semiparametric generalized linear models. Journal of the Royal Statistical Society: Series B (Statistical Methodology) 73, 1 (2011), 3–36.Google ScholarCross Ref
- Sebastian Zepf, Monique Dittrich, Javier Hernandez, and Alexander Schmitt. 2019. Towards Empathetic Car Interfaces: Emotional Triggers while Driving. In Extended Abstracts of the 2019 CHI Conference on Human Factors in Computing Systems. 1–6.Google ScholarDigital Library
Recommendations
Emotion Recognition Using Physiological Signals
MIDI '15: Proceedings of the Mulitimedia, Interaction, Design and InnnovationIn this paper the problem of emotion recognition using physiological signals is presented. Firstly the problems with acquisition of physiological signals related to specific human emotions are described. It is not a trivial problem to elicit real ...
Towards the design of a system to measure emotions using physiological signals as Biofeedback: case study in higher education students
REHAB '19: Proceedings of the 5th Workshop on ICTs for improving Patients Rehabilitation Research TechniquesPeople frequently face situations that change their emotional state, either positively or negatively. Emotions are becoming a form of phylogenetic universal language that is more and more necessary in the area of communication to express ideas, moods or ...
Affective ranking of movie scenes using physiological signals and content analysis
MS '08: Proceedings of the 2nd ACM workshop on Multimedia semanticsIn this paper, we propose an approach for affective ranking of movie scenes based on the emotions that are actually felt by spectators. Such a ranking can be used for characterizing the affective, or emotional, content of video clips. The ranking can ...
Comments