Ni Nyoman Eny Perimawati, Roy Rudolf Huizen, Dandy Pramana Hostiadi

Optimization Model for Fake Account Detection on Twitter (X) Social Media using Feature Engineering and Machine Learning Approaches

Introduction

Optimization model for fake account detection on twitter (x) social media using feature engineering and machine learning approaches. Detect fake accounts on Twitter (X) using an optimized machine learning model with feature engineering. Achieves up to 99.94% accuracy, aiding cybercrime forensics and improving social media credibility.

Abstract

Twitter (X) has become an important platform for community interaction, but this also creates serious challenges due to the proliferation of fake accounts that can harm users and undermine credibility. Previous studies have proposed detection methods but often lacked forensic analysis based on extracted feature information. This study utilizes labeled datasets and supervised evaluation metrics (precision, recall, and F1-score) to validate model performance. Extracting behavioral information from features is crucial for achieving accurate and reliable detection results. The study introduces a novelty in the form of engineered behavioral features that significantly enhance detection accuracy, achieving up to 99.94% using AdaBoost. The proposed approach detects fake accounts on Twitter (X) by extracting key feature information and developing an optimal detection method through machine learning algorithms, including Random Forest, SVM, and AdaBoost. Furthermore, the model is optimized using feature engineering techniques. The novelty of this work lies in the development of engineered features through distribution analysis based on data characteristics and the improvement of classification performance through feature engineering optimization. The initial experiment without feature engineering shows that Random Forest achieved the highest accuracy of 98.77%, followed by AdaBoost at 98.57% and SVM at 95.90%. After applying feature engineering, performance improved, with AdaBoost reaching 99.94%, Random Forest 99.69%, and SVM 99.32%. The proposed model can assist system analysts in detecting fake accounts and contribute to solving forensic cybercrime challenges, particularly in identifying fake social media profiles.

Review

This paper addresses the critical and timely issue of fake account detection on Twitter (X), a pervasive problem that undermines platform credibility and user safety. The authors propose an optimization model leveraging feature engineering and various machine learning approaches, specifically Random Forest, SVM, and AdaBoost. A key contribution highlighted is the development of novel engineered behavioral features derived from distribution analysis, which are claimed to significantly boost detection accuracy. The study positions itself as a practical solution for forensic analysis and cybercrime challenges, promising highly accurate and reliable detection results through its optimized methodology. The methodology demonstrates a clear strength in its systematic approach to improving model performance. The abstract effectively conveys the iterative process of starting with baseline machine learning models, meticulously developing engineered features based on data characteristics, and then re-evaluating performance. The reported improvements are substantial, with AdaBoost showing an impressive jump from 98.57% to 99.94% accuracy after feature engineering. Similarly, Random Forest and SVM also exhibit significant gains, reaching 99.69% and 99.32% respectively. These results underscore the powerful impact of thoughtful feature engineering on classification tasks, providing a strong foundation for assisting system analysts in combating fake profiles. While the reported accuracy figures are exceptionally high and promising, further insights into the characteristics of the labeled dataset, such as its size, diversity, temporal relevance, and class balance, would provide crucial context for assessing the model's generalizability and robustness against evolving fake account strategies. Additionally, a discussion on the computational complexity and scalability of the feature engineering process and the optimized models would be beneficial for real-world deployment scenarios, especially given the dynamic nature and sheer volume of data on social media platforms. Nonetheless, the paper presents a compelling advancement in fake account detection, offering a solid basis for future research into adaptive and scalable solutions for social media forensics.

Full Text

Comments

You need to be logged in to post a comment.