Exploring Critical Eye-Tracking Metrics for Identifying Cognitive Strategies in Raven's Advanced Progressive...

The present study utilized a recursive feature elimination approach in conjunction with a random forest algorithm to assess the efficacy of various features in predicting cognitive strategy usage in Raven's Advanced Progressive Matrices. In addition to item response accuracy (RA) and response time (RT), five key eye-tracking metrics were examined: proportional time on matrix (PTM), latency to first toggle (LFT), rate of latency to first toggle (RLT), number of toggles (NOT), and rate of toggling (ROT). The results indicated that PTM, RLT, and LFT were the three most critical features, with PTM emerging as the most significant predictor of cognitive strategy usage, followed by RLT and LFT. Clustering analysis of these optimal features validated their utility in effectively distinguishing cognitive strategies. The study's findings underscore the potential of specific eye-tracking metrics as objective indicators of cognitive processing while providing a data-driven method to identify strategies used in complex reasoning tasks.