Towards Responsible and Trustworthy Educational Data Mining: Comparing Symbolic, Sub-Symbolic, and Neural-Symbolic AI Methods

This paper compares symbolic, sub-symbolic, and neural-symbolic AI methods for predicting 7th-grade mathematics performance in Estonian primary school students using self-regulated learning data, evaluating generalizability and interpretability across balanced and imbalanced datasets. The study demonstrates that neural-symbolic AI better integrates cognitive, metacognitive, and motivational factors for more responsible and trustworthy educational data mining.

Given the demand for responsible and trustworthy AI for education, this study evaluates symbolic, sub-symbolic, and neural-symbolic AI (NSAI) in terms of generalizability and interpretability. Our extensive experiments on balanced and imbalanced self-regulated learning datasets of Estonian primary school students predicting 7th-grade mathematics national test performance showed that symbolic and sub-symbolic methods performed well on balanced data but struggled to identify low performers in imba

Source

Framework Categories

Tool Types

Tags