The rise of social networks has transformed communication, information sharing and entertainment, but it has also facilitated the rise of harmful activities such as the spread of misinformation, often through the use of social bots. These automated accounts that mimic human behaviour have been implicated in significant events, including political interference and market manipulation. In this paper, we provide a comprehensive review of recent advances in social bot detection, with a particular focus on the role of generative AI and large language models. We present a new categorisation scheme for bots that aims to reduce class overlap while maintaining generality. In addition, we analyse the most commonly used datasets and state-of-the-art classification techniques, and through user profile-based measures, we use Explainable Artificial Intelligence (XAI) and data mining techniques to uncover factors that contribute to bot misclassification. Our findings contribute to the development of more robust detection methods, which are essential for mitigating the impact of malicious bots on online platforms.
The increasing influence of social media has amplified the risks associated with automated accounts that spread misinformation, manipulate public opinion and carry out malicious activities. To address this challenge, this study presents an explainable, feature-based approach for detecting social bots on (formerly Twitter) using user-profile information derived from account metadata and content characteristics. We consolidate and extend existing research by bringing together one of the most comprehensive feature sets explored to date, combining raw attributes, features proposed in the literature, and newly introduced credibility and engagement indicators, together with a previously unexploited profile-personalisation signal. Through a feature engineering and selection process that integrates Mutual Information, Random Forest Importance, and SHAP values, we evaluate the contribution of each feature category and assess its generalisation capacity across three benchmark datasets. Our experiments demonstrate that classical machine learning models enriched with the selected features can match or surpass several state-of-the-art approaches while preserving interpretability. Furthermore, we propose and validate, on the more recent and challenging TwiBot-22 dataset, three categories of features (universal, common, and dataset-specific) that provide a transparent and adaptable basis for generalisable bot detection.
The importance of social media in our daily lives has unfortunately led to an increase in the spread of misinformation, political messages and malicious links. One of the most popular ways of carrying out those activities is using automated accounts, also known as bots, which makes the detection of such accounts a necessity. This paper addresses that problem by investigating features based on the user account profile and its content, aiming to understand the relevance of each feature as a basis for improving future bot detectors. Through an exhaustive process of research, inference and feature selection, we are able to surpass the state of the art on several metrics using classical machine learning algorithms and identify the types of features that are most important in detecting automated accounts.