A project on analysing extracted tweets - (Scraped using Twint). For this project I chose to extract tweets about the supermarket gaint Coles during the period of March -2020, when Australia was at it's peak on COVID - 19 cases and when the supermarket shelves were empty due to high demand of products as people feared a lockdown.
These are the things you would need for executing this project.
Python installed on your machine (or) use Google Colab.
A list of libraries to install for this project.
Twint - An advanced twitter scraping package
nest_asyncio - Module to patch asyncio to allow nested use of asyncio.run
pyLDAvis - To extract info. from a fitted LDA topic model to generate an interactive web-based visualization
Pandas - For data analysis and manipulation
Numpy - Array processing package in python
Seaborn - data visualization library based on matplotlib
Matplotlib - library to write 2-dimensional graphs and plots
Textblob - Python NLP libraries – for textual data processing
Logging - logging system as a part of its standard library
Gensim - a python natural library processing library
Tempfile - module to create temporary files and directories
Scikit-learn - an efficient predective analysis tool and also used for machine learning
NLTK - Natural language processing toolkit in python