Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{177682,
        author = {mayur and Manik Gupta and Kuldeep and Vipul Tyagi},
        title = {fake account detection on social media},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {8588-8596},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=177682},
        abstract = {Social media platforms are experiencing the 
huge snowballing of fake accounts due to the large scale 
developing of this problem which lead to misinformation, 
spam, identity fraud and cyber threats. Fake accounts 
fake public opinion, propagate propaganda and enable 
fraud — so social media is ripe for misuse.Current 
detection techniques (Manual Moderation, Rule-based 
filtering etc) fail to cope with the evolving nature of these 
emerging threats.In the paper we present a hybrid 
machine learning (ml) and natural language processing 
(nlp) framework for effective fake account detection.Our 
tech leverages blockchain technology to create a 
decentralized, 
and untrustful trust verification 
mechanism which significantly increase the security of 
our service and also reduce possibility of account 
cloning. The detection system is constructed applying 
Flask for real-time operation, so that fake accounts can 
be easily identified with behavioral analysis, text patterns, 
and metadata indicators. While we use NLP models to 
evaluate user-generated content and detect malwares in 
text based on sentiments analysis as well linguistic 
characteristics. Moreover, block chain guarantees the 
non-repeateable veracity; it cannot create fake accounts 
on own without anyone's acknowledge.Accuracy: 92% 
(outperform all traditional methods like for sentiment 
analysis, deepfake detection and hash malware 
identification) It has been designed to be scalable and can 
be deployed across various social media platforms like 
Twitter, Facebook or Instagram with ease. Possible 
future works are focused on applying streaming data 
analysis in order to improve real-time detection 
capabilities; also bridging the gap between explainable 
AI (XAI) and decision-making for making the most 
transparent what will happen. Using ML, NLP and 
blockchain together as our approach delivers a good and 
scalable solution towards reducing the fake accounts as 
there risks, making social media secure [sustainable], 
protecting user interactions shield and rebuilding trust 
upon digital communication.},
        keywords = {Real time analysis Fake account detection,  Machine Learning, Natural Language Processing,  Blockchain Flask Social media security Fraud detection  Misinformation detection XAI (explainable AI ),  cybersecurity, Spam detection.)},
        month = {May},
        }