As part of the 2017 Government Legislative Openness Week we at K-Monitor aimed to make Parliamentary data more accessible. The following is a preliminary summary of our project: PARLDATA.

While there is a great amount of information available there, their database and search engine are not user friendly. Out team decided to make this data easily accessible and useful through PARLDATA. Our first results are displaying the lexical diversity of the texts analysed, party breakdown of lexical diversity, and the themes spoken of in Parliament. Using the delitescent Dirichlet allocation with machine learning we identified 19 main groups. 

Our goal with this project is to make use of the parliamentary data available for researchers, journalists and those interested in public matters. We plan to establish our tool on an easily usable website with a search engine capable of handling complex requests. This showcased is just the very first step, we further plan to profile MPs and parties based on the lexicality of their speeches and their favoured topics, with the ability to compare these.

Part I: Language of the Parliament [EN] 
Part II: Speeches in the Parliament [HU]