IEEE-Submit
Twitter is a microblogging and social networking service, which gives us access to large scale social data, particularly about people’s social life. We use it to determine the sentiments of the tweets. In this report, we try to determine a model that classifies the tweets in categories of different linguistic aspects: Directed Hate, Generalized Hate, Sarcasm, Allegation, Justification, Refutation, Support and Oppose. Here, we explore elementary Machine Learning algorithms, Multinomial Naive Bayes and Random Forest Classifier with sampled data selection to improve stance classification at greater efficiency than baseline models.
For trying out the notebooks , go to "Testing Notebook and Data" folder.
This is part of IEEE BigMM Data Challenge 2020.