Abstract: Social media sites such as Twitter have become an integral part of our daily lives. With the growing popularity of these sites, the problem of spamming has also increased, leading to a cluttered and irrelevant feed. To address this problem, we propose a machine learning-based approach to filter out spam messages from social media feeds.
Our approach involves preprocessing the social media feed to extract relevant features such as message content, user activity, and metadata. We then use supervised machine learning algorithms such as Naïve Bayes, Random Forest, and Support Vector Machines to train our model on a labeled dataset of spam and non-spam messages.
We evaluate the performance of our approach using various metrics such as precision, recall, and F1 score. Our experimental results show that our approach achieves high accuracy in detecting spam messages, with an F1 score of over 90%. We also compare our approach with other state-of-the-art methods and demonstrate its superior performance.
Our machine learning-based spam filtering approach can help social media users to have a cleaner and more relevant feed, save time, and protect against potential phishing attacks. The proposed approach can be extended to other social media sites and can be integrated into existing social media platforms to provide users with a seamless spam filtering experience.
Keywords: Support vector machine, Phishing attacks, Random Forest, Naïve bayes, Microblogging, Computer-aided, Artificial neural network
|
DOI:
10.17148/IJARCCE.2023.12315
