Towards Responsible and Trustworthy Educational Data Mining: Comparing Symbolic, Sub-Symbolic, and Neural-Symbolic AI Methods
🤖 AI Summary
This study addresses trustworthiness challenges in educational data mining, specifically targeting generalizability and interpretability of self-regulated learning prediction under class-imbalanced data. Method: Using Estonian elementary students’ mathematics performance prediction as a case study, we systematically compare symbolic AI (decision trees, rule induction), sub-symbolic AI (XGBoost, MLP), and neuro-symbolic AI (an enhanced Neuro-Symbolic Concept Learner). We propose a novel neuro-symbolic framework grounded in educational psychology theory to jointly ensure knowledge traceability and enhanced data-driven capability. Contribution/Results: Our approach reveals, for the first time, fundamental theoretical differences among the three paradigms in modeling factor dependency structures. Empirical evaluation shows a 23% improvement in identifying low-performing students, while robustly integrating motivational, metacognitive, and knowledge dimensions. The resulting predictions are theoretically coherent, human-interpretable, and empirically robust.
Application Category
📝 Abstract
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 imbalanced datasets. Interestingly, symbolic and sub-symbolic methods emphasized different factors in their decision-making: symbolic approaches primarily relied on cognitive and motivational factors, while sub-symbolic methods focused more on cognitive aspects, learned knowledge, and the demographic variable of gender -- yet both largely overlooked metacognitive factors. The NSAI method, on the other hand, showed advantages by: (i) being more generalizable across both classes -- even in imbalanced datasets -- as its symbolic knowledge component compensated for the underrepresented class; and (ii) relying on a more integrated set of factors in its decision-making, including motivation, (meta)cognition, and learned knowledge, thus offering a comprehensive and theoretically grounded interpretability framework. These contrasting findings highlight the need for a holistic comparison of AI methods before drawing conclusions based solely on predictive performance. They also underscore the potential of hybrid, human-centered NSAI methods to address the limitations of other AI families and move us closer to responsible AI for education. Specifically, by enabling stakeholders to contribute to AI design, NSAI aligns learned patterns with theoretical constructs, incorporates factors like motivation and metacognition, and strengthens the trustworthiness and responsibility of educational data mining.
Problem
Research questions and friction points this paper is trying to address.
Evaluates AI methods for responsible educational data mining
Compares generalizability and interpretability of different AI approaches
Addresses limitations in identifying low performers in imbalanced datasets
Innovation
Methods, ideas, or system contributions that make the work stand out.
Neural-symbolic AI enhances generalizability and interpretability
Hybrid NSAI integrates motivation, cognition, and metacognition factors
NSAI compensates underrepresented classes in imbalanced datasets
🔎 Similar Papers
No similar papers found.
