RF-GNN: Random Forest Boosted Graph Neural Network for Social Bot Detection

However, the existence of automated accounts, also known as social bots, has brought many problems to social media. These bots have been employed to disseminate false information, manipulate elections, and deceive users, resulting in negative societal consequences [1; 2; 3]. Effectively detecting bots on social media plays an important role in protecting user interests and ensuring stable platform operation. Therefore, the accurate detection of bots on social media platforms is becoming increasingly crucial. Random Forest (RF) [4] is a classical algorithm of ensemble learning that can significantly improve the performance of the base classifier, Decision Tree (DT) [5]. Specifically, S sub-training sets are generated by randomly selecting n samples with replacement from the original training set of N samples S times. Then, m features are selected from the M-dimensional features of each sub-training set, and S base classifiers are trained using different sub-training sets. The final classification result is determined by the voting of the base classifiers. Due to its excellent performance, RF has been widely applied in various competitions, such as data mining and financial risk detection, and is also frequently used in social bot detection.