Decoding Green Consumption Behavior Among Chinese Consumers: Insights from Machine Learning Models on Emotional and Social Influences

Abstract

This study examined the diverse factors influencing green consumption behavior among Chinese consumers through a comprehensive, data-driven approach that integrated multiple machine learning models, including Gaussian naïve Bayes, K-nearest neighbor, multilayer perceptron, and XGBoost models. By analyzing emotional, product-related, cultural, social, and personal dimensions, this research identified key determinants that shape consumer engagement in sustainable consumption. Unlike conventional studies that rely on linear models or survey-based analyses, this study leveraged machine learning to uncover complex, nonlinear interactions between these factors. The findings reveal that emotional drivers, particularly guilt and pride, play a pivotal role in green consumption decisions, while cultural and product-related factors also exhibit significant influence. This study contributes methodologically by employing a multidimensional, multilevel analytical framework, enhancing the robustness of the findings. Furthermore, the results underscore the importance of policy and marketing strategies that effectively target emotional and social influences to cultivate a sustainable consumer culture. These insights provide actionable recommendations for policymakers and businesses seeking to promote green consumption and advance global sustainability efforts.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 8 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.