Combating Hostility: Covid-19 Fake News and Hostile Post Detection in Social Media
This work addresses the problem of identifying misinformation and hostile content on social media, which is crucial for maintaining public discourse integrity during events like a pandemic, primarily for social media platforms and content moderators.
This paper describes a system developed for the CONSTRAINT shared task at AAAI-2021, focusing on COVID-19 fake news detection in English and hostile post detection in Hindi. The system achieved a 94.39% weighted f1-score for fake news detection using SVM with tf-idf features, and 86.03% (coarse-grained) and 50.98% (fine-grained) f1-scores for hostile post detection using Label Powerset SVM with n-gram features.
This paper illustrates a detail description of the system and its results that developed as a part of the participation at CONSTRAINT shared task in AAAI-2021. The shared task comprises two tasks: a) COVID19 fake news detection in English b) Hostile post detection in Hindi. Task-A is a binary classification problem with fake and real class, while task-B is a multi-label multi-class classification task with five hostile classes (i.e. defame, fake, hate, offense, non-hostile). Various techniques are used to perform the classification task, including SVM, CNN, BiLSTM, and CNN+BiLSTM with tf-idf and Word2Vec embedding techniques. Results indicate that SVM with tf-idf features achieved the highest 94.39% weighted $f_1$ score on the test set in task-A. Label powerset SVM with n-gram features obtained the maximum coarse-grained and fine-grained $f_1$ score of 86.03% and 50.98% on the task-B test set respectively.