Clayton Epp
ABSTRACT
The ability to recognize emotions is an important part of building intelligent computers. Emotionally-aware systems would have a rich context from which to make appropriate decisions about how to interact with the user or adapt their system response. There are two main problems with current system approaches for identifying emotions that limit their applicability: they can be invasive and can require costly equipment. Our solution is to determine user emotion by analyzing the rhythm of their typing patterns on a standard keyboard. We conducted a field study where we collected participants' keystrokes and their emotional states via self-reports. From this data, we extracted keystroke features, and created classifiers for 15 emotional states. Our top results include 2-level classifiers for confidence, hesitance, nervousness, relaxation, sadness, and tiredness with accuracies ranging from 77 to 88%. In addition, we show promise for anger and excitement, with accuracies of 84%.
- Admit One Security. AdmitOneSecurity. http://www.admitonesecurity.com.Google Scholar
- Bender, S. and Postley, H. Key sequence rhythm recognition system and method.Google Scholar
- Bergadano, F., Gunetti, D., and Picardi, C. Identity verification through dynamic keystroke analysis. Intell. Data Anal. 7, 5 (2003), 469--496. Google ScholarDigital Library
- Bergadano, F., Gunetti, D., and Picardi, C. User authentication through keystroke dynamics. ACM Trans. Inf. Syst. Secur. 5, 4 (2002), 367--397. Google ScholarDigital Library
- Brown, M. and Rogers, S. J. User identification via keystroke characteristics of typed names using neural networks. Int. J. Man-Mach. Stud. 39, 6 (1993), 999--1014. Google ScholarDigital Library
- Carroll, L. Alice's Adventures in Wonderland. The Gutenberg Project, 2008.Google Scholar
- Chen, D. and Vertegaal, R. Using mental load for managing interruptions in physiologically attentive user interfaces. CHI '04 ext. abst. on Human fac. in comp. systems, ACM (2004), 1513--1516. Google ScholarDigital Library
- Coan, J. and Allen, J. Handbook of Emotion Elicitation and Assessment. Oxford University Press, New York, USA, 2007.Google ScholarCross Ref
- De Silva, L. and Suen Chun, H. Real-time facial feature extraction and emotion recognition. Infor., Comm., and Sig. Proc. 2003 and the 4th Pac. Rim Conf. on Multimedia, (2003).Google Scholar
- Dowland, P. and Furnell, S. A Long-term trial of keystroke profiling using digraph, trigraph, and keyword latencies. In IFIP Intern. Fed. for Infor. Processing. Springer Boston, 2004, 275--289.Google Scholar
- Drummond, C. and Holte, R. C4.5, class imbalance, and cost sensitivity: why under-sampling beats over-sampling. (2003).Google Scholar
- Ekman, P. Basic Emotions. John Wiley & Sons, Ltd, 2005.Google Scholar
- Epp, C. Identifying emotional states through keystroke dynamics. 2010. http://library2.usask.ca/theses/available/etd-08312010-131027/.Google Scholar
- Fairclough, S. Fundamentals of physiological computing. Inter. with Comp. 21, 1-2 (2009), 133--145. Google ScholarDigital Library
- Gaines, R., Lisowski, W., Press, S., and Shapiro, N. Authentication by keystroke timing: some preliminary results. 1980.Google Scholar
- Gunetti, D. and Picardi, C. Keystroke analysis of free text. ACM Trans. Inf. Syst. Secur. 8, 3 (2005), 312--347. Google ScholarDigital Library
- Gunetti, D., Picardi, C., and Ruffo, G. Keystroke analysis of different languages: a case study. In Lecture Notes in Computer Science. Springer Berlin / Heidelberg, 2005, 133--144. Google ScholarDigital Library
- Hall, M. Correlation-based feature subset selection for machine learning. 1999.Google Scholar
- Hektner, J., Schmidt, J., and Csikszentmihalyi, M. Experience Sampling Method: Measuring the Quality of Everyday Life. Sage Publications, Thousand Oaks, 2007.Google Scholar
- Jain, A., Duin, R., and Mao, J. Statistical pattern recognition: a review. IEEE Transactions on Pattern Analysis and Machine Intelligence 22, 1 (2000), 4--37. Google ScholarDigital Library
- Joyce, R. and Gupta, G. Identity authentication based on keystroke latencies. Commun. ACM 33, 2 (1990), 168--176. Google ScholarDigital Library
- Khan, M. M., Ingleby, M., and Ward, R. D. Automated facial expression classification and affect interpretation using infrared measurement of facial skin temperature variations. ACM Trans. Auton. Adapt. Syst. 1, 1 (2006), 91--113. Google ScholarDigital Library
- Lang, P. Behavioral treatment and bio-behavioral assessment: computer applications. Technology in mental health care delivery systems, (1980), 119--137.Google Scholar
- Mandryk, R. L. and Atkins, M. S. A fuzzy physiological approach for continuously modeling emotion during interaction with play technologies. Int. J. Hum.-Comput. Stud. 65, 4 (2007), 329--347. Google ScholarDigital Library
- Monrose, F. and Rubin, A. D. Keystroke dynamics as a biometric for authentication. Future Gener. Comput. Syst. 16, 4 (2000), 351--359. Google ScholarDigital Library
- Partala, T., Surakka, V., and Vanhala, T. Real-time estimation of emotional experiences from facial expressions. Interact. Comput. 18, 2 (2006), 208--226. Google ScholarDigital Library
- Picard, R. W. Affective Computing. MIT Press, Cambridge, 2007. Google ScholarDigital Library
- Russell, J. Core affect and the psychological construction of emotion. Psychological Review 110, 1 (2003), 145--172.Google ScholarCross Ref
- Sheng, Y., Phoha, V., and Rovnyak, S. A parallel decision tree-based method for user authentication based on keystroke patterns. IEEE Transactions on Systems, Man, and Cybernetics 35, 4 (2005), 826--833. Google ScholarDigital Library
- Stern, R. M., Ray, W. J., and Quigley, K. S. Psychophysiological recording. Oxford University Press, New York, 2001.Google Scholar
- Vizer, L. M., Zhou, L., and Sears, A. Automated stress detection using keystroke and linguistic features: An exploratory study. Int. J. Hum.-Comput. Stud. 67, 10 (2009), 870--886. Google ScholarDigital Library
- Ward, R. D. and Marsden, P. H. Physiological responses to different web page designs. Int. J. Hum.-Comput. Stud. 59, 1-2 (2003), 199--212. Google ScholarDigital Library
- Wilson, G. and Sasse, M. Do users always know what's good for them? Utilizing physiological responses to assess media quality. (2000), 327--339.Google Scholar
- Witten, I. and Frank, E. Data Mining: Practical machine learning tools and techniques. Morgan Kaufmann, San Francisco, 2005. Google ScholarDigital Library
- Zimmermann, P., Guttormsen, S., Danuser, B., and Gomez, P. Affective computing - a rationale for measuring mood with mouse and keyboard. Inter. J. of Occ. Saf. and Ergo. 9, 4 (2003), 539--551.Google ScholarCross Ref
Index Terms
- Identifying emotional states using keystroke dynamics
Recommendations
Acting emotions: physiological correlates of emotional valence and arousal dynamics in theatre
IMX '22: Proceedings of the 2022 ACM International Conference on Interactive Media ExperiencesProfessional theatre actors are highly specialized in controlling their own expressive behaviour and non-verbal emotional expressiveness, so they are of particular interest in fields of study such as affective computing. We present Acting Emotions, an ...
Psychological responses to simulated displays of mismatched emotional expressions
Embodied agents are often designed with the ability to simulate human emotion. This paper investigates the psychological impact of simulated emotional expressions on computer users with a particular emphasis on how mismatched facial and audio ...
Recognizing the emotional state of human and virtual instructors
AbstractStudents' learning from an instructional video could be affected by the instructor's emotional stance during a lesson. A first step in investigating this emotional design hypothesis is to determine whether students perceive the ...
Highlights- This research investigated whether participants are able to recognize the emotional tone of instructors in video clips.
Comments