Tsimperidis, I., Katos, V. and Clarke, N., 2015. Language Independent Gender Identification Through Keystroke Analysis. Information and Computer Security, 23 (3), 286 -301.
Full text available as:
s1-ln1758457095844769-1939656818Hwf-815345003IdV167036923417584570PDF_HI0001.pdf - Accepted Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.
Purpose – In this work we investigate the feasibility of iden tifying the gender of an author by measuring the keystroke duration when typing a message. Design/methodology/approach – Three classifiers were constructed and tested. We empirically evaluated the effectiveness of the classifiers by using empirical data. We used primary data as well as a publicly available dataset containing keystrokes from a diff erent language to validate the language independence assumption. Findings – The results of this work indicate that it is possible to identify the gender of an author by analyzing keystroke durations with a probability of success in the region of 70%. Research limitations/implications – The proposed approach was validated with a limited number of participants and languages, yet the statistical tests show the significance of the results. However, t his approach will be further tested with other languages. Practical implications – Having the ability to identify the gender of an aut hor of a certain piece of text has value in digital forensics, as the proposed method will be a source of circumstantial evidence for “putting fingers on keyboard” and for arbitrating cases where the true origin of a message needs to be identified. Social implications – If the proposed method is included as part of a text composing system (such as email, and instant messaging applications) it could increase trust toward the applications that use it and may also work as a deterrent for crimes involving forgery. Originality/value – The proposed approach combines and adapts techniques from the domains of biometric authentication and data classification.
|Uncontrolled Keywords:||keystroke dynamics; keystroke duration; gender recognition; user classification|
|Group:||Faculty of Science & Technology|
|Deposited By:||Unnamed user with email symplectic@symplectic|
|Deposited On:||26 Aug 2016 10:15|
|Last Modified:||26 Aug 2016 10:15|
Downloads per month over past year
|Repository Staff Only -|