Using Social Networks to detect Malicious Bangla Text Content

Abstract

Social spam has rapidly increased over recent years. This kind of spam contents like text messaging or comments has a massive negative influence on normal user’s experience in social media. Our research reflects the current experimental study on spam detection from different textual data. In this experimental research, we have used Naïve Bayes classifier, a supervised machine learning algorithm with feature extraction to detect spam from Bangla text at the sentence level. We have started this research by collecting Bangla textual data from YouTube, Facebook, and other social media. Then we have categorized the sentences into two polarities i.e. spam and ham applied to the Multinomial Naïve Bayes classification algorithm. Our proposed system detects spam on the basis of the polarity of each sentence associated with it. Finally, our experiment shows that the model has an accuracy of 82.44% in detecting spam Bangla text content.