Toeing the Party Line: Election Manifestos as a Key to Understand Political Discourse on Twitter
Maximilian Maurer, Tanise Ceron, Sebastian Pad\'o, Gabriella Lapesa

TL;DR
This paper presents a method to analyze political discourse on Twitter by predicting party positions using hashtags to fine-tune text representations, enabling reliable analysis without manual annotation even in low-resource, noisy social media data.
Contribution
It extends manifesto-based political positioning methods to Twitter data by leveraging hashtags for automatic fine-tuning, improving robustness in low-resource scenarios.
Findings
Method produces stable political positioning aligned with manifestos.
Effective even with limited and short-term Twitter data.
No manual annotation required for reliable analysis.
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSocial Media and Politics
MethodsContrastive Learning · Sentence-BERT
