WorldCloud and Sentiment Analysis of Gary Vee's Tweets in Python. The tweets scraped were from January 1st 2020 until January 12th 2021.
- PIL - Image processing library
- Pandas - DataFrame Library
- Numpy - Mathematical Library
- Matplotlib - Library used for visualizations
- Wordcloud - Library used for making wordclouds
- NLTK - NLP Library
- Snscrape - Scraper for Social networks services
Using python's package manager pip to install the dependencies
pip install pandas
pip install PIL
pip install matplotlib
pip install wordcloud
pip install git+https://github.com/JustAnotherArchivist/snscrape.gitPython 3.8 or higher is required for snscrape
Using snscrape to scrape the tweets from Twitter.
Execute the following command on the terminal
snscrape --jsonl --progress --since 2020-01-01 twitter-search "from:garyvee" > Gary_data.json--jsonl: Saves as a Json file
--progress: Displays progress every 100 tweets scraped
--since: The time from when the tweets should be scraped
--twitter-search: twitter keyword to search from
The result tweets are saved as the Gary_data.json file.
The GaryVeeWC.ipynb contains the code and outputs for WorldCloud and Senitment Analysis. It should be executed in either Jupyter Notebooks or Google Collab.