Clustering energy support beliefs to reveal unique sub-populations using self-organizing maps
Americans’ support for energy sources is quite complex and dependent on a range of socio-demographic characteristics. In a novel approach to investigate energy opinions on renewables and fossil fuels, self-organizing maps are employed to cluster individuals solely on their energy beliefs using socia...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-07-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844023055597 |
| _version_ | 1797771347076579328 |
|---|---|
| author | Heather Bedle Christopher R.H. Garneau Alexandro Vera-Arroyo |
| author_facet | Heather Bedle Christopher R.H. Garneau Alexandro Vera-Arroyo |
| author_sort | Heather Bedle |
| collection | DOAJ |
| description | Americans’ support for energy sources is quite complex and dependent on a range of socio-demographic characteristics. In a novel approach to investigate energy opinions on renewables and fossil fuels, self-organizing maps are employed to cluster individuals solely on their energy beliefs using social survey data collected from Pew Research in the Spring of 2021. These energy preference clusters are then used in regression models to examine attitudes regarding energy policy in the United States. Results from the self-organizing map (SOM) analysis reveal four distinct clusters: energy traditionalists who oppose renewable sources due to partisan ideologies; energy renewers who strongly prefer investment in only renewable energy sources; energy universalists who universally support all forms of energy; and the aberrant cluster, individuals who prefer solar power greatly over wind energy but demonstrate no other energy preference patterns. Results from regression analyses reveal that SOM clusters are highly predictive of attitudes regarding energy policy. Taken together, these results reveal the unique capability of machine learning to categorize human attitudes – which should be of particular interest to energy policymakers when considering the opinions of the electorate. |
| first_indexed | 2024-03-12T21:36:11Z |
| format | Article |
| id | doaj.art-22f5e0d658e64722b74eedb1be5a8dd3 |
| institution | Directory Open Access Journal |
| issn | 2405-8440 |
| language | English |
| last_indexed | 2024-03-12T21:36:11Z |
| publishDate | 2023-07-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj.art-22f5e0d658e64722b74eedb1be5a8dd32023-07-27T05:59:20ZengElsevierHeliyon2405-84402023-07-0197e18351Clustering energy support beliefs to reveal unique sub-populations using self-organizing mapsHeather Bedle0Christopher R.H. Garneau1Alexandro Vera-Arroyo2School of Geosciences, University of Oklahoma, USA; Corresponding author.Department of Sociology, University of Oklahoma, USASchool of Geosciences, University of Oklahoma, USAAmericans’ support for energy sources is quite complex and dependent on a range of socio-demographic characteristics. In a novel approach to investigate energy opinions on renewables and fossil fuels, self-organizing maps are employed to cluster individuals solely on their energy beliefs using social survey data collected from Pew Research in the Spring of 2021. These energy preference clusters are then used in regression models to examine attitudes regarding energy policy in the United States. Results from the self-organizing map (SOM) analysis reveal four distinct clusters: energy traditionalists who oppose renewable sources due to partisan ideologies; energy renewers who strongly prefer investment in only renewable energy sources; energy universalists who universally support all forms of energy; and the aberrant cluster, individuals who prefer solar power greatly over wind energy but demonstrate no other energy preference patterns. Results from regression analyses reveal that SOM clusters are highly predictive of attitudes regarding energy policy. Taken together, these results reveal the unique capability of machine learning to categorize human attitudes – which should be of particular interest to energy policymakers when considering the opinions of the electorate.http://www.sciencedirect.com/science/article/pii/S2405844023055597Energy preferencesSelf-organizing mapsRenewable energyFossil fuels |
| spellingShingle | Heather Bedle Christopher R.H. Garneau Alexandro Vera-Arroyo Clustering energy support beliefs to reveal unique sub-populations using self-organizing maps Heliyon Energy preferences Self-organizing maps Renewable energy Fossil fuels |
| title | Clustering energy support beliefs to reveal unique sub-populations using self-organizing maps |
| title_full | Clustering energy support beliefs to reveal unique sub-populations using self-organizing maps |
| title_fullStr | Clustering energy support beliefs to reveal unique sub-populations using self-organizing maps |
| title_full_unstemmed | Clustering energy support beliefs to reveal unique sub-populations using self-organizing maps |
| title_short | Clustering energy support beliefs to reveal unique sub-populations using self-organizing maps |
| title_sort | clustering energy support beliefs to reveal unique sub populations using self organizing maps |
| topic | Energy preferences Self-organizing maps Renewable energy Fossil fuels |
| url | http://www.sciencedirect.com/science/article/pii/S2405844023055597 |
| work_keys_str_mv | AT heatherbedle clusteringenergysupportbeliefstorevealuniquesubpopulationsusingselforganizingmaps AT christopherrhgarneau clusteringenergysupportbeliefstorevealuniquesubpopulationsusingselforganizingmaps AT alexandroveraarroyo clusteringenergysupportbeliefstorevealuniquesubpopulationsusingselforganizingmaps |