Abstract
This research seeks to understand how people's daily behaviors and preferences may influence their perceived importance of environmental, economic, and social issues. To date, a lot of research has been grounded in survey and statistical analysis-based approaches using a broad variety of demographic, behavioral, and issue specific factors to underpin these analyses. This study builds on this body of work, seeking to contrast the merits of statistical analysis and machine learning, and to determine the efficacy of decision tree machine learning approaches that only employ non-identifiable data to estimate people's perceived issue importance based predominantly on behavioral inputs. Results show that statistical analysis can extract the critical demographics that influence perceived issue importance, as well as highlighting some behaviors which consistently influence these importance levels. On the other hand, a machine learning approach, rather than giving significance and strength of relationships, make predictions as to whether certain issues are important to people based not only on demographics but also on a suite of daily behaviors. This tool, which does away with the need for intrusive survey questions, may provide a streamlined policy instrument for policymakers to develop more effective energy policies which align with people's values.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
