Confidence-Aware Learning Assistant

TL;DR

This paper presents a confidence-aware learning system that estimates students' self-confidence during multiple-choice tasks using eye tracking, providing feedback to improve learning accuracy and confidence calibration.

Contribution

It introduces a novel eye-tracking based method to estimate self-confidence in real-time and demonstrates its effectiveness through multiple studies and large-scale data collection.

Findings

Confidence detection accuracy of 81% and 79%.

Increased correct answer rates by 14% and 17% with feedback.

Large-scale data from 72 students analyzing feature effectiveness.

Abstract

Not only correctness but also self-confidence play an important role in improving the quality of knowledge. Undesirable situations such as confident incorrect and unconfident correct knowledge prevent learners from revising their knowledge because it is not always easy for them to perceive the situations. To solve this problem, we propose a system that estimates self-confidence while solving multiple-choice questions by eye tracking and gives feedback about which question should be reviewed carefully. We report the results of three studies measuring its effectiveness. (1) On a well-controlled dataset with 10 participants, our approach detected confidence and unconfidence with 81% and 79% average precision. (2) With the help of 20 participants, we observed that correct answer rates of questions were increased by 14% and 17% by giving feedback about correct answers without confidence and incorrect answers with confidence, respectively. (3) We conducted a large-scale data recording in a private school (72 high school students solved 14,302 questions) to investigate effective features and the number of required training samples.