Reading ability detection using eye-tracking data with LSTM-based few-shot learning

TL;DR

This paper introduces a novel LSTM-based few-shot learning approach for predicting reading ability scores from eye-tracking data, demonstrating improved accuracy with limited training samples.

Contribution

It presents a new method combining LSTM and lightweight neural networks for reading ability detection using minimal data, advancing few-shot learning applications in education.

Findings

Higher accuracy than previous methods in reading ability score prediction

Effective use of few-shot learning with eye-tracking data

Open-source code available for replication

Abstract

Reading ability detection is important in modern educational field. In this paper, a method of predicting scores of reading ability is proposed, using the eye-tracking data of a few subjects (e.g., 68 subjects). The proposed method built a regression model for the score prediction by combining Long Short Time Memory (LSTM) and light-weighted neural networks. Experiments show that with few-shot learning strategy, the proposed method achieved higher accuracy than previous methods of score prediction in reading ability detection. The code can later be downloaded at https://github.com/pumpkinLNX/LSTM-eye-tracking-pytorch.git