Estimating the outcome of UKs referendum on EU membership using e-petition data and machine learning algorithms

Abstract

The United Kingdom's 2016 referendum on membership of the European Union is perhaps one of the most important recent electoral events in the UK. This political sentiment has confounded pollsters, media commentators and academics alike, and has challenged elected Members of the Westminster Parliament. Unfortunately, for many areas of the UK this referendum outcome is not known for Westminster Parliamentary Constituencies, rather it is known for the coarser geography of counting areas. This study uses novel data and machine learning algorithms to estimate the Leave vote percentage for these constituencies. The results are seen to correlate well with other estimates.

The Use of Artificial Intelligence in eParticipation: Mapping Current Research

“…Paper ID F-measure [44,45,47,48,57,58,60,64,66,73,77,80,82,86] Precision [43,45,57,60,62,66,67,73,[76][77][78]80,82,86] Accuracy [43,44,46,62,63,69,70,73,[76][77][78]80,82] Recall [45,52,57,60,62,66,73,77,78,80,82,…”

“…The vast majority of studies on the application of AI in eParticipation concern Citizens and Government Institutions. Reference is made to politicians as potentially interested in the adoption of a proposed application or technology [72,75], as directly interested in the results of research [52] or within the context of parliamentary debates about ePetitions [44]. Voluntary Organizations are mentioned in one study, while Researchers are not mentioned in any study.…”

“…The second category of eParticipation activities pertains to citizens' requests, commonly known as ePetitions. Studies in this domain frequently involve analyzing existing requests to extract citizen opinions [56,59] or derive other insightful conclusions [52]. Efforts are also made to develop methods facilitating citizens in drafting requests [61,86].…”

A worlds-eye view of the United Kingdom through parliamentary e-petitions

“…These UK data have been used in a diverse range of quantitate research studies. These include a desire to understand what linguistic factors may influence the popularity of e-petitions (Clark and Lomax, 2020), the interaction of e-petitions with social media (Asher et al, 2019), the estimation of electoral outcomes (Clark et al, 2018), how the design of a platform can influence usage (Hale et al, 2018), what e-petitions on a single topic tells us about citizens' concerns (Kolosok et al, 2021), and how to group together constituencies (Clark et al, 2017).…”

Introduction. La participation politique en ligne au révélateur du pétitionnement électronique

“…De même, des scientifiques travaillant sur des systèmes et des pays différents y voient un moyen pour l'Union européenne de « faire participer » (Mosca et Santucci, 2009), un outil permettant aux autorités d'obtenir un retour (« feedback ») sur leurs politiques (Panagiotopoulos, Elliman, 2012), un instrument au service de la légitimité des institutions représentatives (Bochel, 2013), un moyen simple et à faible coût pour connaître l'opinion de la population (Puschmann et al, 2017), une forme de sismographe de l'opinion (Morva, 2016), une source d'information à développer (Dumas et al, 2017), voire, dans le cas de la Chine, un instrument qui permettrait une meilleure écoute de la population et une meilleure connaissance des problèmes soulevés (Jiang, Meng, Zhang, 2019 ;Wang, Zhong, 2020). Certains travaux proposent du reste de mettre en place des outils d'analyse automatique des pétitions en vue d'en faire des outils au service de l'action politique, sur le modèle des sondages d'opinion (Hagen et al, 2015(Hagen et al, , 2018Karpf, 2016 ;Clark, Morris, Lomax, 2018). D'autres, à partir du système utilisé en Turquie, concluent même que la procédure a plutôt renforcé le gouvernement central en substituant à des relations plus personnelles une structure hiérarchique informelle (Karkin, Janssen, 2020).…”