Instruction system with eyetracking-based adaptive scaffolding

摘要

A digital instructional environment leverages an infrared eye-tracker to monitor a learner's reading and viewing of text and simulations for subject matter. The system detects out-of-order reading/viewing patterns that could lead to poor comprehension. The digital learning environment communicates with other tutorial components including simulation environments, pedagogical agents and may respond in real-time to such patterns with messages that guide learners (knowledge acquirers) to return to effective reading/viewing patterns so as to promote effective construction of mental model(s) developed during knowledge acquisition/learning.

主权项

1. A computer-based engineering knowledge acquisition system, comprising:
a digital processor supporting a user-interactive training material associated with a respective domain that includes at least one diagram; a display monitor coupled to the processor and rendering to an acquirer-user at least one screen view of the user-interactive training material, the at least one screen view having any of text and graphics in a certain locational arrangement relative to graphical content; and an eye-tracking member coupled to the processor, the eye-tracking member (i) tracking eye movement of the acquirer-user viewing the at least one screen view, and (ii) detecting eye traces of the acquirer-user for the at least one screen view; in response to the detected eye traces, the processor generating a summary of knowledge acquisition patterns of the acquirer-user and assessing whether the acquirer-user has missed viewing one or more regions of the at least one diagram; and a rules engine coupled to the processor, the rules engine performing an evaluation of the acquirer-user's viewing of the at least one screen view based upon the detected eye traces and the generated summary of knowledge acquisition patterns, and the rules engine providing one or more metrics as real-time feedback to a user, the processor comparing the detected eye traces of the acquirer-user to an optimal (learning) acquisition pattern predefined for the at least one screen view, and based on the comparison, the processor determining need to assist the acquirer-user with one or more of the text content and the graphical content of the at least one screen view, and the processor providing a tutorial supplement to the acquirer-user, wherein the display monitor further displays the tutorial supplement at least in the at least one screen view.