Proceedings of the Annual Meeting of the Cognitive Science Society

We know that reading involves a coordination between textual characteristics and visual attention, but what does eye gazeduring reading tell us about comprehension? We addressed this question by training random forest models (a machinelearning technique) to predict reading comprehension from ensembles of interacting global gaze features in a person-generalizable manner. We used data from two prior studies in which readers (Ns = 104, 130) answered multiple-choicecomprehension questions during and/or shortly after ( 30 mins) reading a 6500-word text. The models were highly accurateat predicting reading comprehension assessed during reading at both the page- (AUROC = .882) and participant- level (r= .671; computed by aggregating page-level predictions). Accuracy for the post-reading models was lower (AUROCsbetween .538 and .552; rs between .343 and .373), but significantly above chance baselines. Collectively, these findingsconfirm a link between global eye movement behavior and higher-order outcomes of reading.