Using Context-Based and AI-Enhanced Approaches to Improve Student Engagement and Achievement in Secondary Chemistry Education

Synthesis: Abdikayumova and Madybekova (2026) use a mixed-methods, quasi-experimental design with 93 Grade 10 students in three instructional groups — (a) context-based 7E instructional model integrated with AI tools, (b) the 7E model without contextual/AI components, and (c) conventional teaching — over 12 weeks of secondary chemistry. The experimental group, using PhET interactive simulations and ChatGPT tutoring embedded within the 7E phases, achieved significantly higher post-test scores (large effect size, ANCOVA) and reported the highest engagement. The authors argue that contextualization, structured inquiry, and adaptive AI act synergistically: contextual activities connect abstract chemistry to everyday life, the 7E cycle structures reasoning, and AI provides real-time clarification and tailored explanations.

Design and intervention

• Sample: 93 Grade 10 secondary students, three groups: context-based 7E + AI tools (experimental), 7E without context/AI (comparison), conventional teaching (control).
• Duration: 12 weeks.
• AI tools: PhET interactive simulations and ChatGPT-based tutoring embedded within the 7E inquiry phases.
• Measures: pre-/post-tests and engagement scales (quantitative); observation checklists, reflection forms, and AI usage logs (qualitative).

Findings

• Achievement: ANCOVA showed the experimental group scored significantly higher than both comparison and control groups, with a large effect size.
• Engagement: experimental-group students reported the highest levels of interest and participation.
• Synergy of components: the three elements — contextualization, inquiry (7E), and adaptive AI — functioned synergistically. Contextual activities increased relevance and intrinsic motivation; the 7E cycle structured exploratory reasoning; AI provided real-time clarification and tailored explanations, reduced Misconceptions about AI, and supported self-paced learning.
• Teacher dependence: qualitative data showed the benefits relied on teacher guidance and careful lesson planning, not on the tools alone.

What this means for practice

• Teachers. Combine context-based activities with the 7E cycle and adaptive AI rather than adopting any one alone; the integrated group outscored both the 7E-only and conventional groups with a large effect size.
• Teachers. Expect to do the pedagogical work: qualitative evidence showed the gains depended on teacher guidance and careful lesson planning, not on the tools alone.
• Curriculum designers. Anchor chemistry in real-world contexts and embed simulations and AI tutoring in the inquiry phases, since contextual activities raised relevance and intrinsic Motivation while AI supplied real-time clarification.
• Policymakers. Guarantee equitable access to AI tools and issue clear ethical-use guidance covering privacy and transparency of AI responses.
• Teachers. Use AI as a conceptual scaffold — usage logs showed students sought explanations of mechanisms rather than final answers — and confirm it reduces Misconceptions about AI instead of replacing student reasoning.

Limitations

• The sample is 93 Grade 10 students in a single, region-specific setting over 12 weeks, so the small sample limits broader generalization.
• Engagement was measured partly through a five-point self-report scale (Cronbach's α = 0.84); the authors note students often overestimate engagement, though observation checklists and AI-usage logs were added to triangulate it.
• Variability in teacher implementation, despite fidelity checks, may also have influenced outcomes.
• The authors flag potential novelty effects of the AI tools, so the gains may not persist once the novelty fades.

Citation

Abdikayumova, N., & Madybekova, G. (2026). Using context-based and AI-enhanced approaches to improve student engagement and achievement in secondary chemistry education. Chemistry Teacher International, 8(1), 37–51.