TY - GEN
T1 - Keystroke Dynamics Predict Essay Quality
AU - Likens, Aaron D.
AU - Allen, Laura K.
AU - McNamara, Danielle S.
N1 - Funding Information:
This research is supported in part by the Institute of Education Sciences (R305A120707) and the Office of Naval Research (N00014140343 and N12249156). Any opinions or conclusions expressed are those of the authors and do not represent views of the IES or ONR.
Publisher Copyright:
© CogSci 2017.
PY - 2017
Y1 - 2017
N2 - Language entails many nested time scales, ranging from the relatively slow scale of cultural evolution to the rapid scale of individual cognition. The nested, multiscale nature of language implies that even simple acts of text production, such as typing a sentence, entail complex interactions involving multiple concurrent processes. As such, text production may have much in common with other cognitive phenomena thought to emerge from multiplicative interactions across temporal scales, namely those that exhibit fractal properties. We investigated the relationship between fractal scaling and the quality of produced text. Participants (N=131) wrote essays while their keystrokes were recorded. Fractal analyses were then performed on time series of interkeystroke intervals (IKIs). Results showed that fractal properties characterizing IKIs positively predicted expert ratings of essay quality, even after accounting for essay length. The results support our hypotheses concerning multiscale coordination and text production.
AB - Language entails many nested time scales, ranging from the relatively slow scale of cultural evolution to the rapid scale of individual cognition. The nested, multiscale nature of language implies that even simple acts of text production, such as typing a sentence, entail complex interactions involving multiple concurrent processes. As such, text production may have much in common with other cognitive phenomena thought to emerge from multiplicative interactions across temporal scales, namely those that exhibit fractal properties. We investigated the relationship between fractal scaling and the quality of produced text. Participants (N=131) wrote essays while their keystrokes were recorded. Fractal analyses were then performed on time series of interkeystroke intervals (IKIs). Results showed that fractal properties characterizing IKIs positively predicted expert ratings of essay quality, even after accounting for essay length. The results support our hypotheses concerning multiscale coordination and text production.
KW - essay quality
KW - keystroke
KW - multifractal
KW - text production
KW - writing
UR - http://www.scopus.com/inward/record.url?scp=85066028463&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85066028463&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85066028463
T3 - CogSci 2017 - Proceedings of the 39th Annual Meeting of the Cognitive Science Society: Computational Foundations of Cognition
SP - 2573
EP - 2578
BT - CogSci 2017 - Proceedings of the 39th Annual Meeting of the Cognitive Science Society
PB - The Cognitive Science Society
T2 - 39th Annual Meeting of the Cognitive Science Society: Computational Foundations of Cognition, CogSci 2017
Y2 - 26 July 2017 through 29 July 2017
ER -