A Unified Interpretable Intelligent Learning Diagnosis Framework for Learning Performance Prediction in Intelligent Tutoring Systems

Abstract

Intelligent learning diagnosis is a critical engine of intelligent tutoring systems, which aims to estimate learners’ current knowledge mastery status and predict their future learning performance. The significant challenge with traditional learning diagnosis methods is the inability to balance diagnostic accuracy and interpretability. Although the existing psychometric-based learning diagnosis methods provide some domain interpretation through cognitive parameters, they have insufficient modeling capability with a shallow structure for large-scale learning data. While the deep learning-based learning diagnosis methods have improved the accuracy of learning performance prediction, their inherent black-box properties lead to a lack of interpretability, making their results untrustworthy for educational applications. To settle the abovementioned problem, the proposed unified interpretable intelligent learning diagnosis framework, which benefits from the powerful representation learning ability of deep learning and the interpretability of psychometrics, achieves a better performance of learning prediction and provides interpretability from three aspects: cognitive parameters, learner-resource response network, and weights of self-attention mechanism. Within the proposed framework, this paper presents a two-channel learning diagnosis mechanism LDM-ID as well as a three-channel learning diagnosis mechanism LDM-HMI. Experiments on two real-world datasets and a simulation dataset show that our method has higher accuracy in predicting learners’ performances compared with the state-of-the-art models and can provide valuable educational interpretability for applications such as precise learning resource recommendation and personalized learning tutoring in intelligent tutoring systems.

Graph Neural Networks Enhanced Smart Contract Vulnerability Detection of Educational Blockchain

“…Inspired by the success of deep learning in the fields of data mining [2], [22]- [25], computer vision [6], [8], [17], [20], [21], [26]- [33] and speech processing [10], [12], [15], [34]- [42], this paper proposes a method based on deep learning for smart contract vulnerability detection. We decompile the bytecode file of a smart contract to get the opcode, divide several basic blocks according to the instruction semantics and construct a control flow graph CFG according to the jump order.…”

Application of ontology-based engineering and stem approach in learning

“…The research chose an ontological approach to building a unified educational space, which will take into account the labour market requirements at the national and international levels. The most developed ontology representation language is currently web ontology language (OWL), which extends the capabilities of xtensible markup language (XML), resource description framework (RDF) and RDF Schema [20]- [22].…”

Design and implementation of an AI‐enabled visual report tool as formative assessment to promote learning achievement and self‐regulated learning: An experimental study

“…Cognitive diagnosis is based on students' interaction behaviours (eg, answer data and test data) to mine learners' potential cognitive states (mastery of knowledge points and proficiency levels), and then to predict learners' performance in specific learning tasks (Leighton & Gierl, 2007; Zhao et al., 2020). There are two types of cognitive diagnostic models: psychometrics‐based approaches (Templin & Henson, 2006; Whitely, 1980) and deep learning‐based approaches (De La Torre & Douglas, 2004; Wang et al., 2023). Psychometrics‐based approaches tend to classify learners and exercises based on a certain cognitive perspective.…”

“…The experimental findings indicate that neural networks provide a medium to investigate the fundamental cognitive processes of students. The approach no longer depends on artificially established functions and can model intricate non‐linear interactions between students and test questions (Wang et al., 2023).…”