This Jupyter Notebook uses the python programming language to explore the extraction of tweets using the tweepy API, in order to analyze words most mentioned by the main presidential candidates in Brazil, words referring to location, people's proper names, and names of organizations. This classification is performed by manipulating the text of each tweet, splitting the tweet phrase into separate words, removing stop words, and creating labels. These tasks are performed using natural language processing libraries such as Natural Language Toolkit(NLTK), and SpaCy.
- csv
- matplotlib
- nltk
- pandas
- pymongo
- seaborn
- spacy
- tweepy
- Install the dependencies;
- Run Jupyter Notebook in terminal to see the code in your browser.