Skip to main content
eScholarship
Open Access Publications from the University of California

An Embodied Intelligent Tutor for Literal Concepts Recognition

Abstract

We combine motion captured data with linguistic notions in a game-like intelligent tutoring system, in order to helpelementary school students to better differentiate literal from metaphorical uses of motion verbs, based on embodied in-formation. In addition to the thematic goal, we intend to improve young students attention and spatiotemporal memory, bypresenting sensorimotor data experimentally collected in our motion capturing labs. Furthermore, we examine the accom-plishment of games goals and compare it to curriculums approach. Sixty nine elementary school students were randomlydivided in two experimental groups (game and traditional) and one control group. Two way analysis of variance suggeststhat the experimental groups showed progress in posttests, with game group showing remarkable progress especially inthe verbs/actions presented during the intervention. This finding was considered as a first indication of attentional andspatiotemporal memorys improvement, while the games assistance features cultivated students metacognitive perception.

Main Content
For improved accessibility of PDF content, download the file to your device.
Current View