Always a Bridesmaid: A Machine Learning Approach to Minor Party Identity in Multi-Party Systems

French Bourgeois Laura (), Harell Allison (), Stephenson Laura (), Guay Philippe () and Lysy Martin ()
Additional contact information
French Bourgeois Laura: Department of Psychology, Western University, 1151 Richmond Street, London, Ontario, N6A 3K7, Canada
Harell Allison: Department of Political Science, Université du Québec à Montréal, Montreal, Quebec, H3C 3P8, Canada
Stephenson Laura: Department of Political Science, Western University, London, Ontario, Canada
Guay Philippe: Software Engineer, Independent Researcher, Montreal, Quebec, Canada
Lysy Martin: Department of Statistics and Actuarial Science, University of Waterloo, Waterloo, Canada

Statistics, Politics and Policy, 2023, vol. 14, issue 1, 91-112

Abstract: In multiparty systems, maintaining a distinct and positive partisan identity may be more difficult for those who identify with minor parties, because such parties lack the rich history of success that could reinforce a positive social standing in the political realm. Yet, we know little about the unique nature of minor partisan identities because partisanship tends to be most prominent in single-member plurality systems that tend toward two dominant parties, such as the United States. Canada provides a fascinating case of a single-member plurality electoral system that has consistently led to a multiparty system, ideal for studying minor party identity. We use large datasets of public opinion data, collected in 2019 and 2021 in Canada, to test a Lasso regression, a machine learning technique, to identify the factors that are the most important to predict whether partisans of minor political parties will seek in-group distinctiveness, meaning that they seek a different and positive political identity from the major political parties they are in competition with, or take part in out-group favouritism, meaning that they seek to become closer major political parties. We find that party rating is the most important predictor. The more partisans of the minor party rate their own party favourably, the more they take part in distinctiveness. We also find that the more minor party partisans perceive the major party as favourable, the more favouritism they will show towards the major party.

Keywords: Lasso regression; machine learning; minor political parties; partisanship; in-group distinctiveness; out-group favouritism (search for similar items in EconPapers)
Date: 2023
References: Add references at CitEc
Citations:

Downloads: (external link)
https://doi.org/10.1515/spp-2022-0009 (text/html)
For access to full text, subscription to the journal or payment for the individual article is required.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:bpj:statpp:v:14:y:2023:i:1:p:91-112:n:3

Ordering information: This journal article can be ordered from
https://www.degruyter.com/journal/key/spp/html

DOI: 10.1515/spp-2022-0009

Access Statistics for this article

Statistics, Politics and Policy is currently edited by Joel A. Middleton

More articles in Statistics, Politics and Policy from De Gruyter
Bibliographic data for series maintained by Peter Golla ().