This item is available under a Creative Commons License for non-commercial use only
In the modern world of technological progress, systems and interfaces are becoming more and more complex. As a consequence, it is a crucial to design the human-computer interaction in the most optimal way to improve the user experience. The construct of Mental Workload is a valid metric that can be used for such a goal. Among the different ways of measuring Mental Workload, self-reporting procedures are the most adopted for their ease of use and application. This research is focused on the application of Machine Learning as an alternative to theory-driven approaches for Mental Workload measurement. In particular, the study is aimed at comparing the classification accuracy of a set of induced models, from an existing dataset, to the mental workload indexes generated by well-known subjective mental workload assessment techniques - namely the Nasa Task Load Index and the Workload profile instruments.
Gmyzin, D. (2017) A Comparison of Supervised Machine Learning Classification Techniques and Theory-Driven Approaches for the Prediction of Subjective Mental Workload. Masters dissertation, Dublin Institute of Technology, 2017. doi:10.21427/D7533X