Using cognition and risk to explain the intention-behavior gap on bioenergy production: Based on machine learning logistic regression method

Ke He*, Lihong Ye, Fanlue Li, Huayi Chang, Anbang Wang, Sixuan Luo, Junbiao Zhang

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

13 Citations (Scopus)

Abstract

Bioenergy production is a certain economy energy utilization mode, which is of great economic and ecological benefits. Only when pig farmers have consistent intentions and behaviors to participate in bioenergy production, can the intentions play their role in effectively predicting behaviors. Based on the machine learning logistic regression method, taking biogas produced by swine manure as an example, we explore the role of cognition and risk in bridging the intention-behavior gap in bioenergy production. Unlike previous studies, we find that for bioenergy production, a pro-environmental behavior with positive externalities, an individual's perception of environmental policy plays a better role in driving the intention-to-behavior transition than the individual's perception of bioenergy production. From the risk perspective, our results also suggest that the key factor hindering an intention to change behavior is the individual's risk preferences rather than the degree of risk associated with bioenergy production. Policy makers could consider this observed heterogeneity when it comes to aspects such as greater highlight on environmental policy advocacy, and collaboration with insurance companies to develop products for bioenergy production.

Original languageEnglish
Article number105885
JournalEnergy Economics
Volume108
DOIs
Publication statusPublished - Apr 2022

Keywords

  • Bioenergy production
  • Biogas
  • Intention-behavior gap
  • Machine learning
  • Sustainable development

Fingerprint

Dive into the research topics of 'Using cognition and risk to explain the intention-behavior gap on bioenergy production: Based on machine learning logistic regression method'. Together they form a unique fingerprint.

Cite this