Proceedings of the Annual Meeting of the Cognitive Science Society

Understanding how a person thinks, i.e., measuring a singleindividual’s cognitive characteristics, is challenging becausecognition is not directly observable. Practically speaking, stan-dardized cognitive tests (tests of IQ, memory, attention, etc.),with results interpreted by expert clinicians, represent the stateof the art in measuring a person’s cognition. Three areas ofAI show particular promise for improving the effectiveness ofthis kind of cognitive testing: 1) behavioral sensing, to morerobustly quantify individual test-taker behaviors, 2) data min-ing, to identify and extract meaningful patterns from behav-ioral datasets; and 3) cognitive modeling, to help map ob-served behaviors onto hypothesized cognitive strategies. Webring these three areas of AI research together in a unified con-ceptual framework and provide a sampling of recent work ineach area. Continued research at the nexus of AI and cogni-tive testing has potentially far-reaching implications for soci-ety in virtually every context in which measuring cognition isimportant, including research across many disciplines of cog-nitive science as well as applications in clinical, educational,and workforce settings.