Detection of Spam Bots on Twitter using Machine Learning

Abstract

Twitter is a popularly used microblogging website that is used to share views, opinions, and updates. However, in recent times, an epidemic of spammer accounts have spread across the website causing disorder and chaos among the normal users. These spammers either aim to promote some commercial agenda or disturb the peace in the online environment. Our project aims to analyze the tweets made by users and predict if they might be spammers so that appropriate action can be taken on them. This is done using machine learning. The random forest algorithm has been modified by giving weighted importance to certain variables assigned using domain knowledge that has been obtained from exploratory analysis of various twitter data sets and knowledge from scientific research papers. A bag of words has also been added to the algorithm, in order to quickly identify the key phrases used by spam bots. By identifying the spammers we can systematically report them and create a more peaceful online environment.