This repository contains documents and files for a quantitative text analysis of 17 years of presidential speeches in Mexico. The analysis was visualized using LDAvis to explore the topics and patterns present in these speeches over the years.

• final.html: The HTML file with the final analysis and visualizations.
• final.pdf: The PDF version of the final analysis report.
• speeches_consolidate.RData: The consolidated data scrapped from multiple origins of the speeches used for the analysis.

The objective of this project is to perform a Latent Cluster Analysis on 17 years of presidential speeches in Mexico to identify common themes and changes in discourse over time.

1. Data Collection: Speeches from the past 17 years were collected and preprocessed.
2. General Methods: includes sentiment analysis, word clouds, text diversity, and diferent visualization of weighted words.
3. Latent Dirichlet Allocation (LDA): LDA was used to identify topics within the speeches.
4. Visualization with LDAvis: The LDA results were visualized using LDAvis to provide an interactive exploration to support the report. This can be visualized at LDAvis Visualization.