Misinformation Detection on Online Social Media-A Survey

In the current social media era, people are sharing some pieces of information about different types among each other using various social media platforms. This type of available information is not authentic and reliable so-called misinformation. Nowadays, Detection of misinformation regained large attention among researchers. Misinformation detection is related to the text classification problem and connects the content level of news articles with the detection analysis based on some Machine Learning algorithms like Naive Bayes and Support Vector Machine etc. In the specific domain analysis, labeled data based on reliability domain is rarely available. Previous research work relied on news articles collected from so-called reputable and suspicious websites and labeled accordingly. We leverage fact-checking websites to collect individually-labeled news articles with regard to the veracity of their content and use this data to test the cross-domain generalization of a classifier trained on bigger text collections but labeled according to source reputation. This paper provides a comprehensive survey of misinformation and its detection using various social media platforms. Future directions for research have also been also discussed in this research article. Therefore collecting well-balanced and carefully-assessed training data is a priority for developing robust misinformation detection systems in the future.