Abstract
The sequences of keystrokes that are generated when writing texts contain information about the writer as well as the writing task and cognitive aspects of the writing process. Much research has been conducted in the area of writer identification. However, research on the analysis of writing processes based on sequences of keystrokes has received only a limited amount of attention. Therefore, in this study we try to identify properties of keystrokes that indicate cognitive load of the writing process. Moreover, we investigate the influence of these properties on the classification of texts written during two different writing tasks: copying a text and freeform generation of text. We show that we can identify properties that allow for the correct classification of writing tasks, which at the same time do not describe writer-specific characteristics. However, some properties are the result of an interaction between the typing characteristics of the writer and the writing task.
Original language | English |
---|---|
Title of host publication | Benelearn 2017: Proceedings of the Twenty-Sixth Benelux Conference on Machine Learning |
Pages | 28-35 |
Number of pages | 7 |
Publication status | Published - 2017 |
Event | Annual Belgian-Dutch Conference on Machine Learning (BENELEARN 2017) - Eindhoven, Netherlands Duration: 9 Jun 2017 → 10 Jun 2017 |
Conference
Conference | Annual Belgian-Dutch Conference on Machine Learning (BENELEARN 2017) |
---|---|
Abbreviated title | Benelearn 2017 |
Country/Territory | Netherlands |
City | Eindhoven |
Period | 9/06/17 → 10/06/17 |