Twitter is one of the biggest social media platforms which allows many people to interact with each other by posting their thoughts called tweets, about certain topics or issues. Analyzing the tweets helps to track what's being thought and can give interesting insights, into the sentiments of people, their opinions towards a particular topic, product, service, and the general trends in the community.
The main objective of this task is:
- To find the sentiment of the text data. That is to identify if the tweets have a Negative, Positive, or Neutral sentiment.
- Train, test, and validate machine learning model
- Deploy the best model which fits the data and build a dashboard
- In the main folder there are scripts used to extract the data set
- the data folder contains the twitter data used
- The test folder includes scripts used for unit test
- The two notbook folders contain the data pre-processing and visualization notebooks
- my sql_and_streamlit folder contain the .sql schema ns python script to run the dashboard, it has three pages inclusing the main page
- anaconda jupyter notebook and vscode are the maintools used
- for more https://medium.com/@enggezahegn.w/twitter-data-analysis-280d4e21cb9c