Proceedings of the Annual Meeting of the Cognitive Science Society

The first stage of analyzing eye-tracking data is commonly to code the data into sequences of fixations and saccades.This is usually automated using simple, predetermined rules for classifying ranges of the time series into events, such as “ifthe dispersion of gaze samples is lower than the threshold, then code as a fixation.” More recent approaches incorporateadditional eye-movement categories in automated parsing algorithms, particularly glissades, by using time-varying, data-driventhresholds. We describe an alternative approach using the beta-process auto-regressive hidden Markov model (BP-AR HMM).The BP-AR-HMM offers two main advantages over existing frameworks. First, it provides a statistical model for eye movementclassification rather than a single estimate. Second, the BP-AR-HMM uses a latent process to model the number and natureof the types of eye-movements and hence is not constrained to predetermined categories. We present comparisons betweenBP-AR-HMM parsing and standard analyses on multiple datasets.