Machine learning-based social media bot detection: a comprehensive literature review

Abstract

In today’s digitalized era, Online Social Networking platforms are growing to be a vital aspect of each individual’s daily life. The availability of the vast amount of information and their open nature attracts the interest of cybercriminals to create malicious bots. Malicious bots in these platforms are automated or semi-automated entities used in nefarious ways while simulating human behavior. Moreover, such bots pose serious cyber threats and security concerns to society and public opinion. They are used to exploit vulnerabilities for illicit benefits such as spamming, fake profiles, spreading inappropriate/false content, click farming, hashtag hijacking, and much more. Cybercriminals and researchers are always engaged in an arms race as new and updated bots are created to thwart ever-evolving detection technologies. This literature review attempts to compile and compare the most recent advancements in Machine Learning-based techniques for the detection and classification of bots on five primary social media platforms namely Facebook, Instagram, LinkedIn, Twitter, and Weibo. We bring forth a concise overview of all the supervised, semi-supervised, and unsupervised methods, along with the details of the datasets provided by the researchers. Additionally, we provide a thorough breakdown of the extracted feature categories. Furthermore, this study also showcases a brief rundown of the challenges and opportunities encountered in this field, along with prospective research directions and promising angles to explore.

A Review of Machine Learning and AI-Based Approaches to Detecting Cyberbullying on Social Media

“…When applied to various NLP tasks, deep learning models-which rely on word embeddings-show improvement. This review by, Aljabri et.al [6] (2023), looks at the research that has been published between 2015 and 2022 in the area of bot identification and classification using ML approaches on different social media platforms. A taxonomy was developed based on ML-based methodologies, kind of social media platform, and type of social media bot, with a total of 105 publications reviewed in total.…”

A Fake Profile Detection Model Using Multistage Stacked Ensemble Classification

“…Some of the common ML classifiers are used in the existing works, such as decision trees (DTs) [9], K-nearest neighbors (KNN) [10], logistic regression (LR) [11], random forest (RF) [8], naive Bayes (NB) [12], extreme gradient boosting (XGBoost) [13], and support vector machines (SVMs) [14] for classifying profile data in OSNs. While existing techniques for detecting fake profiles have contributed significantly to the literature, further work is needed to design robust and diverse models capable of successfully addressing the difficulties, especially those introduced by unbalanced datasets [15]. The imbalance in the number of real profiles relative to fake profiles might reduce the reliability of detection algorithms.…”

Phishing URLs Detection Using Sequential and Parallel ML Techniques: Comparative Analysis

“…Moreover, intelligent techniques such as ML and DL are rapidly gaining popularity in the cybersecurity domain and being extensively applied since the previous decade. These techniques owe their success to their capability to learn from available data and thereby extract valuable insights and accurately predict future cases [ 5 , 6 , 7 , 8 , 9 ]. Subsequently, ML can be used to predict whether the websites are phishing or legitimate, including zero-hour websites [ 10 ].…”