Nowcasting the Stance of Social Media Users in a Sudden Vote: The Case of the Greek Referendum

TL;DR

This paper introduces a semi-supervised convolution kernel method to nowcast individual social media users' voting intentions during the 2015 Greek referendum, outperforming text-only models in a real-time setting.

Contribution

It presents a novel semi-supervised approach combining text and network data for real-time stance detection during sudden votes, addressing a gap in existing election prediction models.

Findings

20% F-score improvement over text-only models

Effective in real-time, spontaneous voting scenarios

Robust against competitive baselines

Abstract

Modelling user voting intention in social media is an important research area, with applications in analysing electorate behaviour, online political campaigning and advertising. Previous approaches mainly focus on predicting national general elections, which are regularly scheduled and where data of past results and opinion polls are available. However, there is no evidence of how such models would perform during a sudden vote under time-constrained circumstances. That poses a more challenging task compared to traditional elections, due to its spontaneous nature. In this paper, we focus on the 2015 Greek bailout referendum, aiming to nowcast on a daily basis the voting intention of 2,197 Twitter users. We propose a semi-supervised multiple convolution kernel learning approach, leveraging temporally sensitive text and network information. Our evaluation under a real-time simulation framework demonstrates the effectiveness and robustness of our approach against competitive baselines, achieving a significant 20% increase in F-score compared to solely text-based models.