Exploring the Political Agenda of the European Parliament Using a Dynamic Topic Modeling Approach

This study analyzes the political agenda of the European Parliament (EP)\nplenary, how it has evolved over time, and the manner in which Members of the\nEuropean Parliament (MEPs) have reacted to external and internal stimuli when\nmaking plenary speeches. To unveil the plenary agenda and detect latent themes\nin legislative speeches over time, MEP speech content is analyzed using a new\ndynamic topic modeling method based on two layers of Non-negative Matrix\nFactorization (NMF). This method is applied to a new corpus of all English\nlanguage legislative speeches in the EP plenary from the period 1999-2014. Our\nfindings suggest that two-layer NMF is a valuable alternative to existing\ndynamic topic modeling approaches found in the literature, and can unveil niche\ntopics and associated vocabularies not captured by existing methods.\nSubstantively, our findings suggest that the political agenda of the EP evolves\nsignificantly over time and reacts to exogenous events such as EU Treaty\nreferenda and the emergence of the Euro-crisis. MEP contributions to the\nplenary agenda are also found to be impacted upon by voting behaviour and the\ncommittee structure of the Parliament.\n