Utilizing linguistically enhanced keystroke dynamics to predict typist cognition and demographics

David Guy Brizan, Adam Goodkind, Patrick Koch, Kiran Balagani, Vir Phoha, Andrew Rosenberg

Research output: Contribution to journalArticle

11 Citations (Scopus)

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 distinguish High vs. Low cognitively demanding tasks with accuracy up to 72.39%. Detection of non-native speakers of English is achieved with F1=0.462 over a baseline of 0.166, while detection of female typists reaches F1=0.524 over a baseline of 0.442. Recognition of left-handed typists achieves F1=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.

Original languageEnglish (US)
Article number1959
Pages (from-to)57-68
Number of pages12
JournalInternational Journal of Human Computer Studies
Volume82
DOIs
StatePublished - Jun 14 2015

Fingerprint

typist
cognition
Computer keyboards
Linguistics
Communication
cognitive factors
demographic factors
language
Experiments
linguistics
communication
experiment

Keywords

  • Cognitive load recognition
  • Demography recognition
  • Keystroke dynamics
  • Stylometry
  • Typing production

ASJC Scopus subject areas

  • Hardware and Architecture
  • Engineering(all)
  • Software
  • Human-Computer Interaction
  • Human Factors and Ergonomics
  • Education

Cite this

Utilizing linguistically enhanced keystroke dynamics to predict typist cognition and demographics. / Brizan, David Guy; Goodkind, Adam; Koch, Patrick; Balagani, Kiran; Phoha, Vir; Rosenberg, Andrew.

In: International Journal of Human Computer Studies, Vol. 82, 1959, 14.06.2015, p. 57-68.

Research output: Contribution to journalArticle

Brizan, David Guy ; Goodkind, Adam ; Koch, Patrick ; Balagani, Kiran ; Phoha, Vir ; Rosenberg, Andrew. / Utilizing linguistically enhanced keystroke dynamics to predict typist cognition and demographics. In: International Journal of Human Computer Studies. 2015 ; Vol. 82. pp. 57-68.
@article{5954fa006ffb4ed1a190620f3b111437,
title = "Utilizing linguistically enhanced keystroke dynamics to predict typist cognition and demographics",
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 distinguish High vs. Low cognitively demanding tasks with accuracy up to 72.39{\%}. Detection of non-native speakers of English is achieved with F1=0.462 over a baseline of 0.166, while detection of female typists reaches F1=0.524 over a baseline of 0.442. Recognition of left-handed typists achieves F1=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.",
keywords = "Cognitive load recognition, Demography recognition, Keystroke dynamics, Stylometry, Typing production",
author = "Brizan, {David Guy} and Adam Goodkind and Patrick Koch and Kiran Balagani and Vir Phoha and Andrew Rosenberg",
year = "2015",
month = "6",
day = "14",
doi = "10.1016/j.ijhcs.2015.04.005",
language = "English (US)",
volume = "82",
pages = "57--68",
journal = "International Journal of Human Computer Studies",
issn = "1071-5819",
publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - Utilizing linguistically enhanced keystroke dynamics to predict typist cognition and demographics

AU - Brizan, David Guy

AU - Goodkind, Adam

AU - Koch, Patrick

AU - Balagani, Kiran

AU - Phoha, Vir

AU - Rosenberg, Andrew

PY - 2015/6/14

Y1 - 2015/6/14

N2 - 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 distinguish High vs. Low cognitively demanding tasks with accuracy up to 72.39%. Detection of non-native speakers of English is achieved with F1=0.462 over a baseline of 0.166, while detection of female typists reaches F1=0.524 over a baseline of 0.442. Recognition of left-handed typists achieves F1=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.

AB - 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 distinguish High vs. Low cognitively demanding tasks with accuracy up to 72.39%. Detection of non-native speakers of English is achieved with F1=0.462 over a baseline of 0.166, while detection of female typists reaches F1=0.524 over a baseline of 0.442. Recognition of left-handed typists achieves F1=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.

KW - Cognitive load recognition

KW - Demography recognition

KW - Keystroke dynamics

KW - Stylometry

KW - Typing production

UR - http://www.scopus.com/inward/record.url?scp=84930959332&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84930959332&partnerID=8YFLogxK

U2 - 10.1016/j.ijhcs.2015.04.005

DO - 10.1016/j.ijhcs.2015.04.005

M3 - Article

VL - 82

SP - 57

EP - 68

JO - International Journal of Human Computer Studies

JF - International Journal of Human Computer Studies

SN - 1071-5819

M1 - 1959

ER -