Fake Facebook Profile Detection Using Machine Learning

Fake Facebook Profile Detection Using Machine Learning

IEEE BASE PAPER TITLE:

Enhancing Social Media User’s Trust: A Comprehensive Framework for Detecting Malicious Profiles Using Multi-Dimensional Analytics

IEEE BASE PAPER ABSTRACT:

Information transparency, user privacy, and digital security are significantly vulnerable to the proliferation of counterfeit bot accounts on OSN. Traditional methods for distinguishing these accounts archetypally depend on an inadequate set of features, which hampers their effectiveness in contrast to the progressively sophisticated maneuvers employed by malicious users. A state-of-the-art methodology for Fake Bot Account Detection (FAD) that assimilates sophisticated deep learning techniques to scrutinize multimodal data, such as visual content, temporal activity patterns, and network interactions, to incredulous this challenge Visual features are analyzed using sophisticated methods, including deconstructing into smaller segments and extracting high-level patterns using encoder models. Specialized convolutions are employed to identify dependencies in user behavior over time from sequential data. By aggregating features from connected nodes and considering numerous forms of relationships, network analysis is accompanied by the social graph to learn node representations. A unified representation is created by merging these multimodal features. This representation is then transmitted through a completely associated layer and an activation function to predispose whether a bot account is genuine or counterfeit. The detection accuracy of false bot accounts is improved by integrating these diverse data modalities, which addresses the limitations of single-modality approaches. Compared with conventional methods, the FAD method is validated using the Cresci 2017 dataset, demonstrating substantial enhancements in momentous performance metrics. The consequences suggest that the proposed methodology effectively captures the multifaceted character of fake bot accounts, providing a robust tool for enhancing the security of OSNs.

PROJECT OUTPUT VIDEO:

ALGORITHM / MODEL USED:

Gradient Boosting Classifier, ExtraTrees Classifier, Stacking Classifier.

OUR PROPOSED PROJECT ABSTRACT:

The rapid growth of online social networking platforms has significantly transformed digital communication, with Facebook being one of the most widely used platforms worldwide. However, this growth has also led to a surge in fake profiles created for malicious purposes such as identity theft, phishing, spamming, misinformation dissemination, and online fraud. Detecting such fake accounts has become a critical challenge, as they undermine user trust, compromise privacy, and negatively impact the credibility of social media ecosystems. This project focuses on the automatic detection of fake Facebook profiles using machine learning techniques to enhance platform security and user safety.

The need for this project arises from the limitations of manual verification and rule-based detection mechanisms, which are often time-consuming, less scalable, and ineffective against evolving attacker strategies. With fake profiles becoming increasingly sophisticated, there is a strong requirement for intelligent, data-driven systems that can analyze user behavior patterns and profile attributes to accurately distinguish between genuine and fake accounts. Machine learning provides an effective solution by learning complex relationships from historical data and enabling reliable prediction for unseen profiles.

In this project, a complete web-based fake profile detection system is developed using Python for backend processing, HTML, CSS, and JavaScript for the frontend interface, and the Flask framework for integrating the application components. The system utilizes a dataset containing 600 profile records with carefully selected features such as number of friends, following count, community participation, account age, number of posts shared, URLs shared, photos and videos uploaded, profile photo URLs, average comments per post, likes per post, tags per post, and total number of tags. These features collectively represent behavioral and engagement characteristics of user profiles.

Three machine learning models are implemented and evaluated: Gradient Boosting Classifier, ExtraTrees Classifier, and a Stacking Classifier. The Gradient Boosting Classifier achieved a training accuracy of 100% and a testing accuracy of 95%, while the ExtraTrees Classifier recorded a training accuracy of 100% and a testing accuracy of 96%. The Stacking Classifier, which combines the predictions of multiple base learners, achieved a training accuracy of 100% and a testing accuracy of 95%. To ensure comprehensive evaluation, the system performs performance analysis using metrics such as accuracy, precision, recall, F1-score, confusion matrix, and graphical comparisons across all models.

The developed system demonstrates the effectiveness of machine learning-based approaches in detecting fake Facebook profiles and provides a practical, scalable solution that can assist in reducing malicious activities on social networking platforms.

SYSTEM REQUIREMENTS:

HARDWARE REQUIREMENTS: 

• System : Pentium i3 Processor.
• Hard Disk : 20 GB.
• Monitor : 15’’ LED.
• Input Devices : Keyboard, Mouse.
• Ram : 8 GB.

SOFTWARE REQUIREMENTS: 

• Operating System : Windows 10 / 11.
• Coding Language : Python 3.12.0.
• Web Framework : Flask.
• Frontend : HTML, CSS, JavaScript.

REFERENCE:

SAILAJA TERUMALASETTI AND S. R. REEJA, “Enhancing Social Media User’s Trust: A Comprehensive Framework for Detecting Malicious Profiles Using Multi-Dimensional Analytics”, VOLUME 13, 2025.

👉CLICK HERE TO BUY THIS PROJECT “Fake Facebook Profile Detection Using Machine Learning” SOURCE CODE👈

Frequently Asked Questions (FAQ’s) and Answers

Q1. What is the objective of the Fake Facebook Profile Detection project?

The primary objective of this project is to identify and classify fake and genuine Facebook profiles using machine learning techniques by analyzing user profile attributes and behavioral features.

Q2. Which platform does this project focus on?

The project is designed to detect fake profiles on Facebook by analyzing profile-related data and user activity patterns.

Q3. What technologies are used in this project?

The project is developed using Python for backend processing, HTML, CSS, and JavaScript for the frontend interface, and the Flask framework for integrating the web application with machine learning models.

Q4. Which machine learning algorithms are used in the system?

The system implements three machine learning models: Gradient Boosting Classifier, ExtraTrees Classifier, and a Stacking Classifier to detect fake Facebook profiles.

Q5. What type of dataset is used in this project?

The dataset contains 600 profile records with structured numerical features such as number of friends, following count, account age, posts shared, likes per post, comments per post, URLs shared, photos and videos uploaded, and tagging behavior.

Q6. How does the system detect fake Facebook profiles?

The system analyzes profile features and behavioral patterns using trained machine learning models. Based on the learned patterns, the models classify a given profile as either fake or genuine.

Q7. What performance metrics are used to evaluate the models?

The models are evaluated using accuracy, precision, recall, F1-score, confusion matrix, and graphical performance analysis to ensure reliable and consistent results.

Q8. What are the benefits of using machine learning for fake profile detection?

Machine learning enables automated detection by learning complex patterns from historical data, reducing manual effort and improving detection accuracy for fake profiles.

Q9. Is the project suitable for academic and final-year submissions?

Yes. This project is well-suited for academic use, final-year projects, and research demonstrations due to its practical implementation, clear methodology, and measurable performance outcomes.