The dataset being used is the sentiment140 dataset which contains 16,00,000 tweets extracted using the Twitter API. The tweets have been annotated (0 = Negative, 4 = Positive) and they can be used to detect sentiment. A comparative study has been done using three different algorithms:

• Naïve Bayes Algorithm
• Linear SVM Algorithm
• Logistic Regression Algorithm

Click on this link if the Jupyter Notebook does not open: https://nbviewer.jupyter.org/github/lakkshh/Comparitive-Study-on-Sentiment-Analysis-Algorithms/blob/main/Twitter%20Sentiment%20Analysis.ipynb