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

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.

Enhancing Student Performance Prediction on Learnersourced Questions with SGNN-LLM Synergy

“…Furthermore, we pioneer the integration of NLP technology to extract intrinsic knowledge essential for accurate MCQ responses, offering a solution to the cold start problem. Although previous student performance prediction research seldom leveraged NLP advancements, recent studies underscore the potential of integrating advanced NLP in education to unravel question intricacies (Ni et al 2022). We posit that MCQ response accuracy hinges on students' comprehension of underlying knowledge within questions.…”