Evaluating the efficacy of ChatGPT in environmental education: findings from heuristic and usability assessments

Purpose: This study aims to investigate ChatGPT’s potential in environmental education concerning sustainable development goals. Heuristic evaluation and usability testing identify critical usability issues, including inadequate multimedia support, language barriers and insufficient fact-checking capabilities. 

Design/methodology/approach: The study uses heuristic evaluation and usability testing to assess ChatGPT’s efficacy in environmental education at a Chinese higher education institution. The evaluation identifies essential limitations, including reliance on text-only resources, absence of multimedia assets, technical deficiencies, language barriers, lack of fact-checking tools, context-related issues, delayed information, inconsistency and limited expertise. Data was collected through quantitative and qualitative analysis, with input from experts and students. 

Findings: Findings suggest that while ChatGPT offers opportunities for interactive learning, its limitations hinder comprehensive educational outcomes. A proposed hybrid model combining generative AI and human elements aims to enhance engagement and learning effectiveness. This research offers a foundation for integrating AI tools into environmental education, addressing usability gaps and fostering sustainable learning environments. 

Originality/value: This research contributes to a deeper understanding of the role of artificial intelligence in environmental education and underscores the importance of incorporating human intervention. The proposed hybrid approach offers a framework for creating more comprehensive and meaningful learning environments by leveraging the unique strengths of human engagement alongside generative AI technology.