Hostility Detection and Covid-19 Fake News Detection in Social Media
This addresses the problem of harmful content and misinformation on social media, particularly for Hindi and English users, but is incremental as it applies existing NLP methods to new datasets.
The paper tackles detecting hostile content in Hindi social media and COVID-19 fake news in English tweets, achieving a 0.97 F1 score for hostility detection and a 0.93 F1 score for fake news detection.
Withtheadventofsocialmedia,therehasbeenanextremely rapid increase in the content shared online. Consequently, the propagation of fake news and hostile messages on social media platforms has also skyrocketed. In this paper, we address the problem of detecting hostile and fake content in the Devanagari (Hindi) script as a multi-class, multi-label problem. Using NLP techniques, we build a model that makes use of an abusive language detector coupled with features extracted via Hindi BERT and Hindi FastText models and metadata. Our model achieves a 0.97 F1 score on coarse grain evaluation on Hostility detection task. Additionally, we built models to identify fake news related to Covid-19 in English tweets. We leverage entity information extracted from the tweets along with textual representations learned from word embeddings and achieve a 0.93 F1 score on the English fake news detection task.