Identifying innovation in environmental management within higher education institutions: an artificial intelligence text mining-driven model

Purpose This study aims to develop a valid attribute structure aimed at increasing innovation in environmental management (IEM) within higher education institutions (HEIs) using an artificial intelligence (AI) text mining-driven model. Design/methodology/approach This study uses a technology–organization–environment framework and leverages an AI text mining-driven model in a hybrid method to develop a hierarchical attribute structure of IEM attributes. Findings The findings suggest that decision-makers must focus on sustainability ranking, reputation pressures, environmental research programs, regulatory compliance for green building standards and peer institution sustainability benchmarking pressures. Originality/value Prior studies have identified attributes that facilitate IEM. However, there has been inadequate attention paid to developing a thorough structure with which to help HEIs implement systemic IEM that aligns technological adoption with organizational capacity amid increasing external environmental pressures (e.g. regulatory compliance, stakeholder expectations and competitive pressures), which must be included in this structure because HEIs often exhibit limited intrinsic motivation for environmental stewardship. This leads to reactive compliance-oriented approaches that are ineffective in stimulating substantial technological and organizational progress and developing a competitive advantage in environmental management