We can place ourselves in a situation where the government would like to follow political trends and find out if the population has a positive opinion on the country's politics.
The dataset consists of comments on Danish political articles on social media. The comments have a positive or negative score depending on their content. It would then be interesting to be able to make a model that would automatically classify (positive or negative) comments.
We have two R notebooks:
- The first contain the linear Regression
- the second the Neural network.
To run the code:
- You need to install the required packages and run the entire notebook.
- Put the path to the file all_sentences.csv in the read.csv() like this => Corpus <- read.csv("C:/Users/adrie/OneDrive/Documents/sem9/NLP/all_sentences.csv", header = FALSE)