Detecting cognitive and physical stress through typing behavior

Abstract

Monitoring of cognitive and physical function is central to the care of people experiencing or at risk for various health conditions, but existing solutions rely on intrusive methods that are inadequate for continuous tracking. This research explores the possibility of detecting cognitive and physical stress by monitoring keyboard interactions with the eventual goal of detecting acute or chronic changes in cognitive and physical function. Preliminary results indicate that it is possible to classify cognitive and physical stress conditions relative to non-stress conditions based on keystroke and text features with accuracy rates comparable to those currently obtained using affective computing methods. The proposed approach is attractive because it requires no additional hardware, is unobtrusive, is adaptable to each user, and is very lowcost.

Detecting emotional stress during typing task with time pressure

“…To evoke users' stress in the experiments, there are some methods which are widely adopted, which include mental arithmetic, N-back number recall, time pressure, reading aloud, viewing affective picture or video, emotive text reading and story telling (see [6]- [9]). Among these methods, some are very useful to enable the job demands to be quantified or measured, for example mental arithmetic, N-back number recall and time pressure.…”

“…To classify stress versus non-stress conditions, besides the traditional social science research methods, the most common approaches are physiological measurements [8], [12]- [17] and www.conference.thesai.orgfacial expressions recognition [9], [18]- [23]. Although both physiological measures and facial expression recognition have high accuracy rates, but the assessments could be obtrusive, requiring additional equipment (which can be costly), and are often labour or computationally intensive [6], [24]. To eliminate the downsides of both methods above, several research utilized mouse behaviour or keyboard behaviour analyses.…”

“…To model user behaviour using keystroke dynamics, various attributes that can be extracted from the typing pattern of a user must be collected and examined, which include how quickly they type (keystroke speed), the duration of a key is pressed (Down-Up time), the latency between successive keypresses (Down-Down time), the key-press ordering, the usage of shift keys, deletion keys (backspace key and delete key) [25] . In a research by Vizer et al [6], which monitored users' cognitive and physical stress using keystroke dynamics and free-text analysis, the results show that users demonstrated different typing behaviours such as changes of patterns in key latency, keystroke speed, delete keys, navigation keys and other keys (such as letter and number keys) . Therefore stress detection through keystroke dynamics and free-text analysis is possible.…”

Predictive biometrics: a review and analysis of predicting personal characteristics from biometric data

“…The authors in [181] reports a process to develop an understanding of a subject's physiological status and predict stress, and the authors in [145] uses a variety of physiological signals to predict emotion, where body physiological characteristics such as cardiac function, temperature, muscle electrical activity, respiration, skin conductance and electrical activity of the brain are collected. The study reported in [182] detects both cognitive and physical stress by monitoring keystroke, and the authors in [183] presents a new approach to assessing emotional experience from users during computer‐based interaction, using software which collects physiological measurements including heart rate, sweating (skin conductivity), muscle tension, and respiration rates.…”

Continuous Stress Monitoring under Varied Demands Using Unobtrusive Devices

“…Self-reporting is believed more relevant as only the participant knows how stressed that he or she felt. On the other side, mouse and keyboard dynamicsdriven approaches, are considered as new methods that are able to collect inner state information from a user automatically , where research by (Carneiro Lim et al, 2014aLim et al, , 2014bLim et al, , 2015aLim, Ayesh, & Stacey, 2016a;Lim et al, 2016b;Vizer, 2009)have shown the correlations between stress and keyboard and mouse dynamics. Therefore, we would like to examine whether the mouse and keyboard dynamics-driven approaches could be used to predict what a user perceives.…”