The objective of this study was to see if it could be used as a tool to maintain student engagement with course material via. In this scenario, the Social Media platform employed for interaction with students outside of classtime was Facebook. This exploratory case study was a follow up exercise to a similar piece of research that was done regarding the usage of Twitter outside of the classroom. We also consider the possibility that language-based, fake news classification, on such short statements is an ill-posed problem.
These include bias and the fact that they do not really model veracity which makes them prone to adversarial attacks. Yet, after evaluating the models' behaviour, numerous flaws appeared. We achieved higher accuracy than previous studies that used more data or more complex models. A simple neural network (FcNN) was also used to enhance each model's result by utilising the sources' reputation scores 1. We investigate the application of transformer models BERT, RoBERTa and ALBERT that have previously performed significantly well on several natural language processing tasks including text classification. In this paper we attempt to determine if state-of-the-art models, trained on the LIAR dataset can be leveraged to reliably classify short claims according to 6 levels of veracity that range from "True" to "Pants on Fire".
Early detection of fake news is therefore a critical but challenging problem. Fake news refers to deceptive online content and is a problem which causes social harm.
0 kommentar(er)
