Dual input stream transformer for vertical drift correction in eye-tracking reading data
This addresses the bottleneck of manual line assignment in reading research, though it appears to be an incremental improvement over existing methods.
The paper tackles the problem of assigning fixation points to correct text lines in eye-tracking reading data, which is crucial due to vertical drift noise. Their Dual Input Stream Transformer (DIST) ensemble combined with a classical approach achieves 98.17% average accuracy across nine datasets.
We introduce a novel Dual Input Stream Transformer (DIST) for the challenging problem of assigning fixation points from eye-tracking data collected during passage reading to the line of text that the reader was actually focused on. This post-processing step is crucial for analysis of the reading data due to the presence of noise in the form of vertical drift. We evaluate DIST against eleven classical approaches on a comprehensive suite of nine diverse datasets. We demonstrate that combining multiple instances of the DIST model in an ensemble achieves high accuracy across all datasets. Further combining the DIST ensemble with the best classical approach yields an average accuracy of 98.17 %. Our approach presents a significant step towards addressing the bottleneck of manual line assignment in reading research. Through extensive analysis and ablation studies, we identify key factors that contribute to DIST's success, including the incorporation of line overlap features and the use of a second input stream. Via rigorous evaluation, we demonstrate that DIST is robust to various experimental setups, making it a safe first choice for practitioners in the field.