article · Discover Artificial Intelligence
Resource-constrained educational settings often lack personalised instructional resources, limiting science learning outcomes. This study evaluated the feasibility of using an artificial intelligence chatbot as an instructional scaffolding tool to support science education. Conducted with 31 pre-Senior High School students in Ghana, the four-week intervention deployed the chatbot as a self-directed learning and inquiry support system within a pre-experimental single-group pre-test and post-test setup. Evaluated using validated instruments, the intervention yielded statistically significant improvements across both cognitive outcomes and broader holistic competencies. Cognitive gains demonstrated large effect sizes, while holistic competencies showed moderate-to-large improvements. In addition, students' self-reported perceptions of the chatbot's utility strongly correlated with their final learning outcomes. The results offer preliminary evidence that AI chatbots can serve as knowledgeable support systems, expanding personalised learning opportunities where traditional resources are limited.
Personalised instruction is frequently unavailable in under-resourced schools, creating substantial barriers to science education. This study demonstrates that conversational AI tools can effectively bridge resource gaps by serving as accessible inquiry partners for students. Demonstrating tangible cognitive and competence gains, the research highlights how low-barrier digital tools can support self-directed learning despite infrastructure and instructional limitations.
The intervention operates at an applied, tested feasibility stage, having completed an initial pilot with 31 students. The technology could inform scalable educational software, self-directed learning applications, and conversational tutoring systems targeted at secondary school students in developing or low-resource educational sectors. Further validation through controlled trials would be required before broader deployment or commercial rollout as an instructional support product.
AI-generated from the published abstract. Always read the original work before citing.
Abstract Artificial Intelligence offers innovative potential for personalised learning, yet its integration remains hindered by instructional voids and restrictive mobile-device policies globally. This study addresses these challenges by investigating AI-powered chatbots as a scalable scaffolding tool for science learning in resource-constrained settings where a scarcity of personalised instructional resources presents a significant barrier to science outcomes. Employing a pre-experimental single-group pre-test/post-test design, the research assessed changes in cognitive outcomes and holistic competencies among 31 pre-Senior High School students in Ghana using researcher-developed, validated instruments. The intervention integrated the chatbot as a self-directed learning and inquiry support system over four weeks. Qualitative data were analysed thematically and subsequently quantified. Quantitative data were analysed using paired t-tests and the robust Wilcoxon signed-rank test, supplemented by Spearman’s rank-order correlation and Least Absolute Deviations (LAD) regression. Findings revealed statistically significant improvements across the measured domains, with large effect sizes observed for cognitive outcomes (Cohen’s d > 2.0) and moderate-to-large effect sizes for holistic outcomes (Wilcoxon r = 0.41–0.68). The findings suggest that the chatbot functioned as a More Knowledgeable Other (MKO) within the structured learning intervention and may have supported cognitive and self-directed learning processes, consistent with Cognitive Load Theory (CLT) and Self-Determination Theory (SDT) interpretations. Critically, the study found a strong positive correlation (ρ > 0.8) between students’ learning outcomes and their self-reported Perception of Utility. This research provides preliminary evidence on the feasibility and potential value of AI-supported learning for expanding personalised learning opportunities in resource-constrained educational contexts.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1007/s44163-026-02113-2
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
