Information-driven attentional capture

Abstract

Visual attention, the selective prioritization of sensory information, is crucial in dynamic, information-rich environments. That both internal goals and external salience modulate the allocation of attention is well established. However, recent empirical work has found instances of experience-driven attention, wherein task-irrelevant, physically non-salient stimuli reflexively capture attention in ways that are contingent on an observer's unique history. The prototypical example of experience-driven attention relies on a history of reward associations, with evidence attributing the phenomenon to reward-prediction errors. However, a mechanistic account, differing from the reward-prediction error hypothesis, is needed to explain how, in the absence of monetary reward, a history of target-seeking leads to attentional capture. Here we propose that what drives attentional capture in such cases is not target-seeking, but an association with instrumental information. To test this hypothesis, we used pre-cues to render the information provided by a search target either instrumental or redundant. We found that task-irrelevant, physically non-salient distractors associated with instrumental information were more likely to draw eye movements (a sensitive metric of information sampling) than were distractors associated with redundant information. Furthermore, saccading to an instrumental-information-associated distractor led to a greater behavioral cost: response times were slowed more severely. Crucially, the distractors had equivalent histories as sought targets, so any attentional differences between them must be due to different information histories resulting from our experimental manipulation. These findings provide strong evidence for the information history hypothesis and offer a method for exploring the neural signature of information-driven attentional capture.

Keywords: Attention; Attention in learning; Attentional capture.

Fig. 1

A Training phase task and information manipulation. Observers have 800 ms to search for a color-defined target and report the orientation of the line inside (horizontal or vertical). Half the trials are pre-cued with reliable information about target color (target matches pre-cue color) and half are pre-cued with unreliable information (target matches one of two pre-cue colors). B Training phase results. Proportion correct (top) and mean response time for correct trials (bottom) for each pre-cued condition; each dot is an individual participant; the outcome of a paired t-test is reported in each scatterplot. C Test phase task and results. Observers have 1,200 ms to search for the shape singleton and report the orientation of the line inside (horizontal or vertical). Half the trials contain an information-associated distractor (instrumental-information-associated or redundant-information-associated). Dotted lines on posterior distributions indicate 95% credible intervals, the dashed line indicates the change in proportion of saccades calculated directly from the data. See main text for additional details