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.
|Title of host publication||Proceedings of the 2nd Workshop on Computational Modeling of People's Opinions, Personality and Emotions in Social Media (PEOPLES 2018), NAACL workshop|
|Publisher||Association for Computational Linguistics|
|Publication status||Published - 2018|
|Event||The 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Workshop on Computational Modeling of People's Opinions, Personality and Emotions in Social Media (PEOPLES) - New Orleans, New Orleans, United States|
Duration: 6 Jun 2018 → 6 Jun 2018
|Conference||The 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies|
|Period||06/06/2018 → 06/06/2018|