Keywords
Applied Machine Learning, Support Vector Machine, Linear Regression, Twitter, Social Network, Anomaly Detection.
Disciplines
Artificial Intelligence and Robotics | Data Science
Abstract
The rapid growth of social networks has led to increased challenges, such as fraud, cyberbullying, and the spread of automated accounts (bots). Detecting anomalies within these networks is essential to maintaining security and trust. This study explored machine learning algorithms: Random Forest, XGBoost, Support Vector Machine (SVM), and Logistic Regression for anomaly detection in social networks, specifically focusing on Twitter bot identification, By applying AI-driven data mining techniques to a dataset of 37,438 Twitter bot accounts dataset, the research evaluates the effectiveness of these models in detecting unusual patterns. XGBoost achieved the highest accuracy (84.9%), with an ROA_AUC of 0.87, followed closely by Random Forest (84.8%). Additionally, enhancement techniques like hyperparameter tuning and class balancing optimize performance and ensure fairness in model predictions. Applying SMOTE improved recall by 20% enhancing bot detection fairness. The findings show that ensemble models outperform linear and margin-based models in detecting automated behavior. The study contributes to advancing reliable AI-based anomaly detection, promoting a safer and more trustworthy digital ecosystem.
Author ORCID Identifier
Rayane ElRaba’a: https://orcid.org/0000-0002-0875-8372
Layal Abu Daher : https://orcid.org/0000-0002-4041-3243
Recommended Citation
El Raba’a, Rayane and Abu Daher, Layal
(2026)
"UNMASKING TWITTER BOTS: AN APPLIED MACHINE LEARNING APPROACH,"
BAU Journal - Science and Technology: Vol. 7:
Iss.
2, Article 6.
DOI: https://doi.org/10.54729/2959-331X.1162
ISSN
2959-331X