ABSTRACT
Fake news emerged as a challenge for society now a day. Easy accessibility and low cost to the internet makes the fake news propagation task easy. In the Covid-19 pandemic situation, it is required to reduce the proliferation of misleading content to reduce its severe impact. Many existing works are based on lexico-syntactic features using a small training sample size. To address this issue, this study used the Gossip-cop dataset for evaluation. Various supervised techniques of the ML model and advanced deep learning techniques are implemented for intense research. Dataset is crawled from Gossipcop fact-checking websites. The dataset consists of 4,947fake news with text and 16,694 real news. The result of these algorithms helps in differentiating false content from reliable news and improved the accuracy achieved using existing techniques. © 2021 IEEE.
ABSTRACT
This paper summarizes the contribution of our team UIBK-DBISFAKENEWS to the shared task “FakeNews: Corona Virus and Conspiracies Multimedia Analysis Task” as part of MediaEval 2021, the goal of which is to classify tweets based on their textual content. The task features the three sub-tasks (i) Text-Based Misinformation Detection, (ii) Text-Based Conspiracy Theories Recognition, and (iii) Text-Based Combined Misinformation and Conspiracies Detection. We achieved our best results for all three sub-tasks using the pre-trained language model BERT Base[1], with extremely randomized trees and support vector machines as runner ups. We further show that syntactic features using dependency grammar are ineffective, resulting in prediction scores close to a random baseline. Copyright 2021 for this paper by its authors.