DeepQR: Neural-based Quality Ratings for Learnersourced Multiple-Choice Questions

TL;DR

DeepQR is a neural network model that improves automated quality assessment of multiple-choice questions by leveraging semantic features, self-attention, and contrastive learning, outperforming existing methods on diverse learnersourced datasets.

Contribution

This paper introduces DeepQR, a novel neural model for question quality rating that integrates semantic analysis, self-attention, and contrastive learning, advancing automated question evaluation.

Findings

DeepQR outperforms six comparative models on university course datasets.

Self-attention effectively captures semantic correlations in MCQs.

Contrastive learning enhances question representation quality.

Abstract

Automated question quality rating (AQQR) aims to evaluate question quality through computational means, thereby addressing emerging challenges in online learnersourced question repositories. Existing methods for AQQR rely solely on explicitly-defined criteria such as readability and word count, while not fully utilising the power of state-of-the-art deep-learning techniques. We propose DeepQR, a novel neural-network model for AQQR that is trained using multiple-choice-question (MCQ) datasets collected from PeerWise, a widely-used learnersourcing platform. Along with designing DeepQR, we investigate models based on explicitly-defined features, or semantic features, or both. We also introduce a self-attention mechanism to capture semantic correlations between MCQ components, and a contrastive-learning approach to acquire question representations using quality ratings. Extensive experiments on datasets collected from eight university-level courses illustrate that DeepQR has superior performance over six comparative models.