Parliamentary Proceeding
Parliamentary proceedings are increasingly being analyzed using computational linguistics techniques to understand political discourse, ideology, and sentiment. Current research focuses on developing multilingual language models, such as those based on BERT and transformer architectures, to process large corpora of transcribed parliamentary speeches and debates, enabling analysis of topics, sentiment, political positioning, and even the identification of pronoun referents. This work facilitates cross-lingual comparative studies in political science and provides valuable tools for researchers and the public to better understand political processes and public engagement with parliamentary activities.
Papers
Multilingual Power and Ideology Identification in the Parliament: a Reference Dataset and Simple Baselines
Çağrı Çöltekin, Matyáš Kopp, Katja Meden, Vaidas Morkevicius, Nikola Ljubešić, Tomaž Erjavec
L(u)PIN: LLM-based Political Ideology Nowcasting
Ken Kato, Annabelle Purnomo, Christopher Cochrane, Raeid Saqur