These days, there are numerous online social media platforms that connect people, such as Instagram, X (formerly Twitter), and Facebook. The vast amount of user-generated content on X has made it a leading social media platform, where users can interact, share updates, and meet new friends. To combat spam, X employs Google Safe Browsing, which detects and blocks spam URLs. However, the platform attracts various types of spammers due to its sophisticated API that allows users to read and publish data. Many previous studies have explored different machine learning algorithms to identify spam on X. Unfortunately, these methods have not been thoroughly tested and often prove inaccurate when applied to large datasets. To address these issues, this study proposes a hybrid approach was proposed in this study by integrating Artificial Neural Networks (ANNs) with Fuzzy Decision Trees to address these problems. The proposed classifier effectively distinguishes between spam and non-spam tweets based on their labels. This work introduces a novel solution by combining a deep learning method with a decision tree classifier. For testing, a large dataset comprising 600 million public tweets was utilized. To evaluate the performance of the proposed algorithm, metrics such as accuracy, F-measure, True Positive Rate (TPR), and False Positive Rate (FPR) were employed. The results demonstrate that the proposed strategy is both reliable and effective.
Author (s) Details
M. Arunkrishna
PG & Research Department of Computer Science, Christhu Raj College
(Affiliated to Bharathidhasan University), Tiruchirappalli, Tamil Nadu, India.
B. Senthilkumaran
PG & Research Department of Computer Science, Christhu Raj College
(Affiliated to Bharathidhasan University), Tiruchirappalli, Tamil Nadu, India.
Please see the book here:- https://doi.org/10.9734/bpi/stda/v9/4809
No comments:
Post a Comment