The DOI matches its Crossref record; 36 of the 37 references it cites were found in a registry or an index.
Identifying emotional states using keystroke dynamics
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%.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Besides its natural use for authentication, KD can also be used to determine the authors' emotional state [102][103][104][105]”
From Online grooming detection: A comprehensive survey of child exploitation in chat logs (2023) · cites this paper as [102]
In the citing paper
“They combine keystroke dynamics, written/oral content, and facial video. These information channels synergistically support investigations into participant emotions9–12, triggered by the experimental stressors.”
From Stress and productivity patterns of interrupted, synergistic, and antagonistic office activities (2019) · cites this paper as [9]
Citations
Cites
Data Mining: Practical Machine Learning Tools and Techniques
Witten, I. H., Frank, E., & Hall, M. A. (2011) · Elsevier eBooks · doi:10.1016/c2009-0-19715-5 · Cited by 25,543
Witten, I. H. (2008) · Cited by 9,143
Picard, R. W. (1997) · MIT Press · doi:10.7551/mitpress/1140.001.0001 · Cited by 7,382
Statistical pattern recognition: a review
Jain, A. K., Duin, P., & Mao, J. (2000) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.824819 · Cited by 6,898
Core affect and the psychological construction of emotion.
Russell, J. A. (2003) · Psychological Review · doi:10.1037/0033-295x.110.1.145 · Cited by 6,113
Experience Sampling Method: Measuring the Quality of Everyday Life
Hektner, J. M., Schmidt, J. A., & Csíkszentmihályi, M. (2006) · Cited by 1,239
The Handbook of emotion elicitation and assessment
(2008) · Choice Reviews Online · doi:10.5860/choice.46-1769 · Cited by 1,128
Technology in mental health care delivery systems
Sidowski, J. B., Johnson, J. H., & Williams, T. A. (1980) · Ablex Pub. Corp. eBooks · Cited by 977
Correlation-based Feature Subset Selection for Machine Learning
Hall, M. A. (1998) · Cited by 959
C4.5, Class Imbalance, and Cost Sensitivity: Why Under-Sampling beats Over-Sampling
Drummond, C., & Holte, R. C. (2003) · Cited by 800
Cited by
Sorted by citations
Personal Sensing: Understanding Mental Health Using Ubiquitous Sensors and Machine Learning
Mohr, D. C., Zhang, M., & Schueller, S. M. (2017) · Annual Review of Clinical Psychology · doi:10.1146/annurev-clinpsy-032816-044949 · Cited by 802
Alberdi, A., Aztiria, A., & Basarab, A. (2015) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2015.11.007 · Cited by 496
Biometric Authentication and Identification Using Keystroke Dynamics: A Survey
Banerjee, S., & Woodard, D. L. (2012) · Journal of Pattern Recognition Research · doi:10.13176/11.427 · Cited by 369
Attitudes towards user experience (UX) measurement
Law, E. L., van Schaik, P., & Roto, V. (2013) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2013.09.006 · Cited by 273
Multimodal data as a means to understand the learning experience
Giannakos, M. N., Sharma, K., Pappas, I. O., Kostakos, V., & Velloso, E. (2019) · International Journal of Information Management · doi:10.1016/j.ijinfomgt.2019.02.003 · Cited by 227
Metadata
- Authors
- Epp, C., Lippold, M., & Mandryk, R. L.
- Affiliations
- University of Saskatchewan (CA)
- ORCID
- Mandryk, Regan L.
- Venue
- Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
- Publisher
- ACM
- Published
- 2011-05-07
- Pages
- 715-724
- OpenAlex
- W1978986669
- Cited by
- 364
- References
- 37
- Citations by year
- 2026: 11 · 2025: 16 · 2024: 14 · 2023: 15 · 2022: 46 · 2021: 25 · 2020: 24 · 2019: 36 · 2018: 15 · 2017: 35 · 2016: 21 · 2015: 31 · 2014: 31 · 2013: 20 · 2012: 19
- FWCI
- 37.63
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- CHI Conference on Human Factors in Computing Systems (publishedVersion)
- Funders
- University of Saskatchewan
- Natural Sciences and Engineering Research Council of Canada
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Emotion and Mood Recognition
- Physical Sciences › Computer Science › Information Systems › User Authentication and Security Systems
- Physical Sciences › Computer Science › Human-Computer Interaction › Gaze Tracking and Assistive Technology
- Keywords
- emotion recognition, keystroke dynamics, typing patterns, emotional state, emotion-aware systems, user modeling, classification accuracy
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
