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 Estonian students' mathematics performance using self-regulated learning data, evaluating generalizability, interpretability, and which cognitive/metacognitive/motivational factors each AI approach emphasizes in its predictions.

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

Study Type

Source

Framework Categories

Tool Types

Tags