Sentiment Analysis on the First Republic Party debate in 2016 based on Python,NLTK and ML | LSTM.
- Sentiment.ipynb contains ML implementation of the problem
- LSTM.ipynb contains a Recurrant Neural Network implementation of the problem
Results: after training 100 epochs (20 minutes)
- average accuracy 81%
- best accuracy 84%
- positive accuracy 50.68%
- negative accuracy 89.98%
Objective: determine the writer's attitude (positive, negative, or neutral) towards a particular topic/product.
API used:
- pandas
Dataset:
- csv file containing first GOP debate (Ohio) tweets to analyze sentiment
More Information: https://www.kaggle.com/ngyptr/python-nltk-sentiment-analysis/notebook
Navigate to the folder
Machine learning and deep learning definitions.docx