Datathon – HackNews – Solution – Task3-Antiganda

Posted 5 CommentsPosted in NLP

Edit: link to github is here: AntigandaNet¶ This will be a deep learning attempt to tackle Task 3 – identifying the exact occurrences of manipulation or propaganda in a string of text. Tools: The deep learning library used is and pytorch. Tokenization is achieved via spacy. Other tools include pandas and numpy. For […]

Datathon – HackNews – Solution – Antiganda (Propaganda Detection)

Posted Leave a commentPosted in NLP

Abstract¶This notebook tries to classify news articles in 2 classes propaganda and non-propaganda. 3 types of models Naive Bayes Classifier, Linear Support Vector Classifier and Recurrent Neural Network. The Linear SVC shows the best results. yesThe neural network comes close, while the Naive Bayes Classifier predicts only one class. The following packages have been used: […]