Bridging the Knowledge–Behavior Gap in Rural Food Systems: Evidence from AI-Driven Visual Agro-Nutrition Education in Nigeria
Onyebuchi-Igbokwe Grace Chizoma *
Department of Fine and Applied Arts, Alvan Ikoku Federal University of Education Owerri, Nigeria.
Ogu Jovita Charles
Department of Fine and Applied Arts, Alvan Ikoku Federal University of Education Owerri, Nigeria.
Egornu Chizoba Anderson
Department of Fine and Applied Arts, Alvan Ikoku Federal University of Education Owerri, Nigeria.
Okwulehie Felicia Chinyere
Department of Home Economics and Hospitality Management, Alvan Ikoku Federal University of Education Owerri, Nigeria.
Uzoegbu, Fiat Mary
Digital Library Unit, Alvan Ikoku Federal University of Education Owerri, Nigeria.
*Author to whom correspondence should be addressed.
Abstract
Food security is a complex, multidimensional global challenge shaped by inequality, climate change, and systemic vulnerabilities, affecting millions worldwide. This study examined the effectiveness of AI-driven visual agro-nutrition education in bridging the persistent knowledge–behavior gap in rural food systems in Nigeria. Despite increasing emphasis on agricultural production, limited nutrition literacy continues to constrain dietary outcomes among smallholder farming households. A quasi-experimental pre-test/post-test control group design was adopted, involving rural households in Ebonyi and Imo States. The intervention consisted of a seven-month exposure to culturally contextualized digitalized visual materials, including infographics, animations, and audiovisual content designed to simplify agro-nutrition concepts. Data were analyzed using descriptive and inferential statistical techniques, including paired sample t-tests, independent sample t-tests, chi-square analysis, analysis of variance (ANOVA), and multiple regression analysis. The findings revealed a statistically significant improvement in agro-nutrition knowledge among participants exposed to the intervention (t = 18.42, p < 0.05), alongside a significant difference between experimental and control groups (t = 21.35, p < 0.05). A significant association was also observed between digital exposure and dietary diversity (χ² = 32.47, p < 0.05), indicating that knowledge gains translated into measurable behavioral change. Regression results identified digital engagement as the strongest predictor of knowledge improvement (β = 0.45), with the model explaining 62% of the variance. The study concludes that visually mediated, technology-enabled agro-nutrition education significantly enhances both cognitive understanding and practical dietary decisions among rural populations. It recommends the integration of digitalized visual learning tools into agricultural extension systems as a scalable and inclusive strategy for improving food security outcomes in low-literacy contexts.
Keywords: Agro-nutrition education, artificial intelligence, dietary diversity, food security, rural households