This project is for News Sentiment Analysis. This project contains implementations of state of the art papers for News Sentiment Analysis. The list of papers is:
Political News Sentiment Analysis for Under-resourced Languages https://www.aclweb.org/anthology/C/C16/C16-1281.pdf
Hierarchical classification in text mining for sentiment analysis of online news https://www.researchgate.net/profile/Jinyanleo_Li/publication/281969696_Hierarchical_classification_in_text_mining_for_sentiment_analysis_of_online_news/links/560006e508aec948c4fa0e07.pdf
Weighted Multi-label Classification Model for Sentiment Analysis of Online News http://lufo.me/docs/BigComp2016.pdf
Sentiment Analysis of Online News Text: A Case Study of Appraisal Theory http://www.ntu.edu.sg/home/assgkhoo/papers/Khoo_et_al.Sentiment_analysis.OIR2012.pdf
Mining Future Spatiotemporal Events and their Sentiment from Online News Articles for Location-Aware Recommendation System http://www.cs.umd.edu/~hjs/pubs/ho-mobigis12.pdf
The data used to train and test is famous polarity dataset from cornell which is movie review dataset Link: http://www.cs.cornell.edu/people/pabo/movie-review-data/. We have used this dataset instead of any news dataset because of unavailabilty of labeled new dataset which is approved universally.
"news.py" program is the implementation of "Hierarchical classification in text mining for sentiment analysis of online news" paper. This paper concludes that removing the highly popar sentiment words from the corpus improves the sentiment analysis. To run: python news.py
To get all the requirements run: pip install -r requirements.txt
Shobhit Sharma sshar107@asu.edu