Identifying writing tasks using sequences of keystrokes: Annual Belgian-Dutch Conference on Machine Learning (BENELEARN 2017)

Rianne Conijn, Menno Van Zaanen

Research output: Other contributionAcademic

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 languageEnglish
Number of pages8
Publication statusPublished - 2017
Externally publishedYes

Fingerprint Dive into the research topics of 'Identifying writing tasks using sequences of keystrokes: Annual Belgian-Dutch Conference on Machine Learning (BENELEARN 2017)'. Together they form a unique fingerprint.

Cite this