Artificial Intelligence for Electronic Waste Management: An Image Recognition Framework for Zanzibar Urban District

Electronic waste (e-waste) continues to pose a major environmental and public health challenge in developing regions, including Zanzibar Urban District. Limited electronic waste management infrastructure and low levels of public awareness contribute to improper disposal practices that harm both human health and the environment. This study employed mixed methods (qualitative and quantitative) to analyse existing literature, digital tools, and conceptual approaches regarding the use of Artificial Intelligence (AI) in electronic waste management. From the review, a subscription-based ChatGPT large language model was employed to support content refinement and system development. Using this large language model (LLM) as the core Artificial Intelligence engine, an integrated solution was developed that combines an image recognition component for automated electronic waste classification with a chatbot module designed to guide users on proper sorting and recycling procedures. Although the study did not implement or evaluate a physical prototype, the proposed framework directly addresses the identified challenges of inefficient electronic waste classification processes and low public awareness in the Zanzibar Urban District. The analysis demonstrates that Artificial Intelligence-enabled systems have the potential to improve the accuracy of electronic waste identification and strengthen user engagement in sustainable disposal practices. The proposed Artificial Intelligence framework, therefore, provides a foundational pathway for future development and real-world implementation of intelligent electronic waste management technologies in similar developing contexts, helping to reduce the environmental and health effects of electronic waste and contributing to a cleaner Zanzibar Urban District