Efficient Framework for Real or Fake Data Detection in Web Content Using Natural Language Processing and Machine Learning Techniques
Online Social media have become an important source of information for a large number of people in the recent years. As the usage of social networks increased, the abuse of the media to spread fake news also increased in many fold. Due to the semantic nature of the contents, the accuracy of automated methods is limited and quite often require manual intervention. The amount of data generated in online social networks is so huge as to make the task computationally expensive to be done in real time. This research propose a methodology to detect fake content using concepts based on Natural Language Processing (NLP) and machine learning techniques. This proposed system would enable prevention of spread of fake information in Twitternetwork.The Machine Learning (ML) techniques such as Support Vector Machine (SVM), Decision Tree (DT), K-Nearest Neighbor, and Adaboost SVM-KNN are applied in this research. After preprocesses and feature extraction over the actual dataset these methods are effectively identifies the fake news with collected dataset and evaluated by the metrics such as accuracy, precision, recall and F1-measure.