Analysis of voting dynamics and its themes in the Chamber of Deputies using Natural Language Processing and Complex Networks

Abstract

The objective of this project is to seek to understand the relationship between deputies, their parties and the vote chosen on various topics in the Chamber of Deputies, in order to map the coalitions, configurations of the bases of support and opposition of presidential mandates, in addition to the physiology of some parties within this body. This will be done by analyzing open data from the Chamber of Deputies, with the help of computational techniques such as Natural Language Processing (NLP) and Complex Network Analysis. First the data through the API made available by the Chamber, then the voting themes will be identified from the texts that describe the votes using NLP and then building a network of relationships between the candidates, their votes, party orientation and themes with the help of graphs. With the network structured, the analysis will be done using Complex Network Analysis techniques. This project will help to understand the political dynamics of the Chamber of Deputies, helping to bring to light the contradictions and interests of members of the Chamber of Deputies, helping in political decision-making and even in a future project democratizing access to this information with a public tool and simplified access to this information.