Detecting and filtering rumor in social media using news media event

In social media platform, many users post messages to express their interests and preferences daily. Because of its fast and easy access abundant people follow news events and there is a possibility for spreading rumor or fake news. This fake news is unverified at the time of posting. Therefore, it is necessary to detect and remove the fake news before it spread widely. Rumors or fake news are created illegally for the purpose of popularity, hike in their business or financial, and so forth, and these rumors need to be detected as easily as possible. Our proposed rumor detection method compares the social media content with news media and applies the support vector machine (SVM) as binary classification technique. Our experiments results revealed that the proposed method attained considerable improvement when compared to the existing machine learning techniques. The proposed SVM rumor detection approach attained better results of 89% precision, 64% recall, and 85% F-measure. The experimental results proved that the proposed method will be useful for avoiding social damages caused by rumors in social media.