Abstract :

Social Media Platforms Such As Twitter Play A Major Role In Information Sharing; However, They Are Increasingly Affected By Fake Tweets And Spam Accounts That Spread Misleading Or Harmful Content. Detecting Such Content Manually Is Impractical Due To The Large Volume And Real-time Nature Of Social Media Data. This Paper Presents TrustLens, A Hybrid Approach For Evaluating Tweet Authenticity By Combining Content-based Deep Learning Analysis With User Profile Evaluation. A Long Short-Term Memory (LSTM) Neural Network Is Employed As The Core Component Of The Proposed System To Analyze Tweet Textual Content And Classify It As Spam Or Non-spam. In Addition, User Profile Attributes Such As Account Age, Follower–following Ratio, Verification Status, And Activity Patterns Are Analyzed To Estimate The Spam Risk Of An Account. The Final Prediction Is Obtained By Integrating Both Content-based And Profile-based Assessments Using A Weighted Fusion Strategy. Experimental Results On A Twitter Spam Dataset Demonstrate That The Proposed Approach Achieves High Accuracy And Improves Detection Reliability Compared To Traditional Machine Learning Models. Keywords— Twitter Spam Detection, Tweet Authenticity, Machine Learning, Deep Learning, LSTM, User Profile Analysis

Published:

17-3-2026

Issue:

Vol. 26 No. 3 (2026)

Page Nos:

269-274

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite