An Ideological Differentiation Methodology Based on Topic Analysis
Digital Humanities, Content analysis, Programmatic dimensions, Political distance, Metrics.
The study seeks to contribute in the field of digital humanities with the automated analysis of the performance of political parties, presenting a new approach to deal with multiple programmatic dimensions, with an ideological aspect. In the field of social sciences, we produce inferences to analyze the content of documents, even complex and multidimensional ones such as those that portray the role of political parties in society. However, how to carry out an automated analysis of these multidimensional party contents under an ideological aspect of analysis? The procedure proposed for carrying out empirical measures of distance on ideological polarization or programmatic differentiation, necessary to test spatial models of political action, bypasses syntactic analysis and prior annotation of documents. The focus is on the use of natural language processing techniques to extract the multiple dimensions - of the party's performance and the theoretical line under which the analysis will be carried out - with a full scan of the digitized collection of documents (corpora) for later comparison, in the light of theory, the degree of affinity between the political parties. The thematic sequence of the dissertation consists of the presentation of different approaches for content analysis of party documents and govern coalitions, the metrics used for this purpose and the applications in Brazil. Finally, we present a new methodology based on topic analysis and the preliminary results achieved.