Multilingual estimation of political-party positioning: From label aggregation to long-input Transformers
This work addresses the need for robust, cross-lingual NLP methods in computational political science, though it is incremental as it compares existing approaches rather than introducing a new paradigm.
The paper tackled the problem of automatically estimating political-party positioning from long texts across multiple languages, comparing label aggregation and long-input Transformer methods on a dataset of 41 countries and 27 languages, finding that label aggregation achieved the best results.
Scaling analysis is a technique in computational political science that assigns a political actor (e.g. politician or party) a score on a predefined scale based on a (typically long) body of text (e.g. a parliamentary speech or an election manifesto). For example, political scientists have often used the left--right scale to systematically analyse political landscapes of different countries. NLP methods for automatic scaling analysis can find broad application provided they (i) are able to deal with long texts and (ii) work robustly across domains and languages. In this work, we implement and compare two approaches to automatic scaling analysis of political-party manifestos: label aggregation, a pipeline strategy relying on annotations of individual statements from the manifestos, and long-input-Transformer-based models, which compute scaling values directly from raw text. We carry out the analysis of the Comparative Manifestos Project dataset across 41 countries and 27 languages and find that the task can be efficiently solved by state-of-the-art models, with label aggregation producing the best results.