NLP Integrated Hybrid Model of Semi-Supervised and Supervised Learning for Online Misinformation Classification

Social media serves as a platform to outsource all kinds of information from politics to entertainment, from health industry to the country’s administration. Some of the posts on these platforms are reliable, but most of them have some proportion of misinformation. The diversity of posts, such as the use of different languages, abbreviating words and messages with hidden meanings, make it more complex to identify the authenticity of the published information. This research will focus on identifying a model to find the misinformation in social media using the NLP integrated hybrid framework that uses a combination of semi-supervised and supervised learning. We use hybrid models that consist of two semi-supervised learning algorithms, namely Label Propagation and Label Spreading, with Logistic Regression and Random Forest as the supervised components. Among them we found that the hybrid model combining Label Propagation and Logistic Regression gives better performance in terms of accuracy, precision, recall, F1-score and AUC performance metrics in order to classify the online misinformation.