Area of interest adaption using feature importance
This work addresses the challenge of compensating for errors and inaccuracies in eye tracking data, particularly in domains like abstract art where manual annotation is difficult, though it appears incremental as an extension of existing data-driven approaches.
The paper tackles the problem of adapting areas of interest (AOI) in eye tracking data to improve classification and qualitative analysis, presenting two algorithms that use feature importance to grow or shrink AOIs, resulting in considerable improvements in classification results for generalized AOIs.
In this paper, we present two approaches and algorithms that adapt areas of interest (AOI) or regions of interest (ROI), respectively, to the eye tracking data quality and classification task. The first approach uses feature importance in a greedy way and grows or shrinks AOIs in all directions. The second approach is an extension of the first approach, which divides the AOIs into areas and calculates a direction of growth, i.e. a gradient. Both approaches improve the classification results considerably in the case of generalized AOIs, but can also be used for qualitative analysis. In qualitative analysis, the algorithms presented allow the AOIs to be adapted to the data, which means that errors and inaccuracies in eye tracking data can be better compensated for. A good application example is abstract art, where manual AOIs annotation is hardly possible, and data-driven approaches are mainly used for initial AOIs. Link: https://es-cloud.cs.uni-tuebingen.de/d/8e2ab8c3fdd444e1a135/?p=%2FAOIGradient&mode=list