Effectiveness of an AI-Assisted Cognitive Load Management Intervention to Improve Geometry Performance Among Students with Learning Disabilities: An Experimental Study

Abstract

Children with learning disabilities (LDs) often experience the cognitive overload. It makes mathematics, and more specifically geometry, particularly challenging for them. Traditional instructional approaches usually fail to address the unique cognitive needs of LD students. This study developed and evaluated an AI-Assisted Cognitive Load Management Strategy (AI-CLMS) for improving geometry performance in LD students. AI-CLMS was designed to manage the cognitive load in LD students using AI platforms which can provide adaptive and personalized instructions. An experimental study was conducted to evaluate whether the AI-CLMS is an effective strategy to improve geometry performance in LD students. A total of 32 purposively selected students were randomly assigned to a control group (n=16) and an experimental group (n=16). The experimental group received three weeks intervention through an AI platform incorporating CLT principles such as content segmenting and progressive complexity while the control group continued with traditional instructions. An 18-item Geometry Performance Assessment (KR-20 = 0.74) was used as a pre-test and post-test data collection tool. Descriptive statistics, Shapiro-Wilk tests, Levene’s test, t-tests and Cohen’s d were performed for data analysis. The data analysis revealed that there was no significant difference in baseline scores of both groups (p = .944). The control group didn’t show significant improvement in post-test (p = .518). Whereas the improvement in post-test scores of the experimental group was significant (t (15) = -4.84, p < .001, d=2.87). Post-test between group comparisons also revealed that the experimental group outperformed the control group (t (30) = -4.68, p < .001) with a large effect size (d = 1.65). These results confirmed that AI-CLMS is an effective strategy to improve the mathematical performance among the LD students. Findings of this study also confirm that AI platforms can be effectively integrated with CLT in order to improve learning in special education.