Uncovering Spam in Twitter: A Machine Learning Approach
Abdul Majid Soomro, Awad Bin Naeem, Susama Bagchi, Neha Vaishnavi Sharma, Pardeep Singh, Sanjoy Kumar Debnath · 2023
Presently, we are living in a digital world where we can interact and speak with anybody on the planet through social networking sites such as Twitter and Facebook. Twitter is the fastest-growing social networking service among many others. Because of its prominence, it deals with a slew of spammers that transmit falsified and misleading material. Researchers had a tough time obtaining un-spammed and legitimate information from Twitter due to this spamming. In this research, we provided a unique way to design/create a system that distinguishes between spammer and authentic account tweets in real-time. For the dataset, we used the Twitter API. Four machine learning classifiers Decision Tree (DT), Support Vector Machine (SVM), Naïve Bayesian (NB), and Logistic Regression (LR) were implemented. We compared the performance of these ML classifiers in terms of accuracy, stability, and scalability and found that the Nave Bayesian classifier provided the best results, i.e., 96.83 % accuracy among all.