Predicting Authorship and Author Traits from Keystroke Dynamics

Written text transmits a good deal of non-verbal information related to the author’s identity and social factors, such as age, gender and personality. However, it is less known to what extent behavioral biometric traces transmit such information. We use typist data to study the predictiveness of authorship, and present first experiments on predicting both age and gender from keystroke dynamics. Our results show that the model based on keystroke features leads to significantly higher accuracies for authorship than the text-based system, while being two orders of magnitude smaller. For user attribute prediction, the best approach is to combine the two, suggesting that extra- linguistic factors are disclosed to a larger degree in written text, while author identity is better transmitted in typing behavior.