CLASSIFYING TWITTER USER AS A BOT OR NOT AND COMPARING DIFFERENT CLASSIFICATION ALGORITHMS.

Abstract

Social media provides a platform for sharing content and news and provides online marketing landscapes for start-ups and companies in their early phase - social media marketing. But, increasing evidence suggests that a growing amount of social media content is generated by autonomous entities known as social bots. These bots have been used for malicious tasks such as spreading false information, spams, malicious contents, etc. The popularity and open structure of Twitter have attracted a large number of automated programs, known as bots [1]. In our work we present a framework or model to detect such entities on Twitter and be able to assist human users in identifying who they are interacting with. We benchmark the classification framework by using a publicly available dataset of Twitter users (both humans and bots). We observe the difference among human and bot in terms of tweeting behavior, tweet content, and account properties. It uses the combination of features extracted from a user to determine the likelihood of being a human or bot.