Toeing the Party Line: Election Manifestos as a Key to Understand Political Discourse on Twitter

Abstract

Political discourse on Twitter is a moving target: politicians continuously make statements about their positions. It is therefore crucial to track their discourse on social media to understand their ideological positions and goals. However, Twitter data is also challenging to work with since it is ambiguous and often dependent on social context, and consequently, recent work on political positioning has tended to focus strongly on manifestos (parties' electoral programs) rather than social media. In this paper, we extend recently proposed methods to predict pairwise positional similarities between parties from the manifesto case to the Twitter case, using hashtags as a signal to fine-tune text representations, without the need for manual annotation. We verify the efficacy of fine-tuning and conduct a series of experiments that assess the robustness of our method for low-resource scenarios. We find that our method yields stable positioning reflective of manifesto positioning, both in scenarios with all tweets of candidates across years available and when only smaller subsets from shorter time periods are available. This indicates that it is possible to reliably analyze the relative positioning of actors forgoing manual annotation, even in the noisier context of social media.

Figures (8)

• Figure 1: Political discourse: Manifestos vs. Twitter
• Figure 2: Illustration of our workflow.
• Figure 3: Experiment 2: Mantel correlation results for SBERTHashtag for subsampled subsets of the dataset for the election years 2017 and 2021. Average over five runs with standard deviation.
• Figure 4: Experiment 3 (b): Results for SBERTHashtag sampling tweets of individual months in the election years 2017 and 2021.
• Figure 5: Two-dimensional projection of politician's SBERTHashtag embedding centroids for the year 2021. Appendix \ref{['appendix:party_names']} introduces party acronyms and names.