Which Identities Are Mobilized: Towards an automated detection of social group appeals in political texts

TL;DR

This paper introduces a machine learning-based method to automatically detect and analyze references to social groups in European political texts, revealing patterns and changes over time and across countries.

Contribution

It combines LLMs and embedding filtering to identify social group appeals in political manifestos, enabling large-scale, cross-national analysis of party strategies.

Findings

No convergence in group appeals despite electoral shifts

Method maps social group references across 15 countries from 1980 to 2021

Approach is adaptable to other text analysis applications

Abstract

This paper proposes a computational text classification strategy to identify references to social groups in European party manifestos and beyond. Our methodology uses machine learning techniques, including BERT and large language models, to capture group-based appeals in texts. We propose to combine automated identification of social groups using the Mistral-7B-v0.1 Large Language Model with Embedding Space-based filtering to extend a sample of core social groups to all social groups mentioned in party manifestos. By applying this approach to RRP's and mainstream parties' group images in manifestos, we explore whether electoral dynamics explain similarities in group appeals and potential convergence or divergence in party strategies. Contrary to expectations, increasing RRP support or mainstream parties' vote loss does not necessarily lead to convergence in group appeals. Nonetheless, our methodology enables mapping similarities in group appeals across time and space in 15 European countries from 1980 to 2021 and can be transferred to other use cases as well.