Volume 17, No. 1, 2020

Enhancing Cyber Security in Twitter: A Data-Driven Approach for Spam Detection and Traffic Classification


Dr. Soumitra Das , Dr. Sunil D. Rathod , Mr. Vikas Nandgaonkar

Abstract

Twitter has become a popular platform for sharing news, opinions, and personal updates. However, it has also become a breeding ground for cyber threats such as spamming, phishing, and hacking. This paper presents a data-driven approach to enhancing cyber security in Twitter through spam detection and traffic classification. We propose a novel system that uses machine learning algorithms to detect and classify spam and non-spam tweets. Our methodology involves collecting a large dataset of tweets, preprocessing the data, and using feature selection and extraction techniques to develop effective models. Our experiments demonstrate the effectiveness of the proposed system in accurately detecting spam and classifying traffic. This paper provides insights into the state-of-the-art in Twitter cyber security and offers recommendations for future research.


Pages: 633-639

Keywords: Machine Learning, Spam Detection, Scalability, Twitter.

Full Text