Utilizing linguistically enhanced keystroke dynamics to predict typist cognition and demographics. Issue 82 (October 2015)

• Record Type: Journal Article
• Authors: Brizan, David Guy; Goodkind, Adam; Koch, Patrick; Balagani, Kiran; Phoha, Vir V.; Rosenberg, Andrew
• Is Part Of: International journal of human-computer studies. Issue 82(2015)
• Page Start: 57
• Page End: 68
• Publication Date: 2015-10
• Subjects: Keystroke dynamics -- Stylometry -- Cognitive load recognition -- Demography recognition -- Typing production; Human-machine systems -- Periodicals; Systems engineering -- Periodicals; Human engineering -- Periodicals; Human engineering; Human-machine systems; Systems engineering; Periodicals; Electronic journals; 004.019
• DOI: 10.1016/j.ijhcs.2015.04.005
• Languages: English
• ISSNs: 1071-5819

Abstract

Abstract: Entering information on a computer keyboard is a ubiquitous mode of expression and communication. We investigate whether typing behavior is connected to two factors: the cognitive demands of a given task and the demographic features of the typist. We utilize features based on keystroke dynamics, stylometry, and "language production", which are novel hybrid features that capture the dynamics of a typists linguistic choices. Our study takes advantage of a large data set (~350 subjects) made up of relatively short samples (~450 characters) of free text. Experiments show that these features can recognize the cognitive demands of task that an unseen typist is engaged in, and can classify his or her demographics with better than chance accuracy. We correctly distinguishHigh vs.Low cognitively demanding tasks with accuracy up to 72.39%. Detection of non-native speakers of English is achieved with F 1 =0.462 over a baseline of 0.166, while detection of female typists reaches F 1 =0.524 over a baseline of 0.442. Recognition of left-handed typists achieves F 1 =0.223 over a baseline of 0.100. Further analyses reveal that novel relationships exist between language production as manifested through typing behavior, and both cognitive and demographic factors. Abstract : Highlights: Recognition of cognitive task with linguistic and keystroke features with accuracy of 72.39%. Recognition of gender, handedness, and native-language from short unconstrained text at F 1=.462, 0.223, and 0.524, respectively. Developed novel Language Production features hybridizing keystroke dynamics and stylometry.