These are the accompanivsdv script and datasets for my sentiment and linear regression analysis.
Fully writen in R, this script executes the entire research. It has 6 different steps:
- Loading and cleaning the data
- Perform the sentiment analysis
- Localize the tweets - Please note that this takes a long time to do. For every tweet the OpenStreetMap API is called.
- Analyses of usable tweets
- Perform linear regression
- Optimization of the model
All the datasets are collected and made public by Gabriel Preda on Kaggle. The datasets I used were created at 22-06-2021. If you require this data, the Twitter data can be found here and the vaccination data is available at this location.