A Method of Machine Learning for Social Bot Detection Combined with Sentiment Analysis

Social Bot exists widely in major social networks. Some maliciously use a social bot to guide public opinion, steal user privacy, and create rumors, which seriously affects the security of social networks. Past approaches mainly extracted large amounts of contents but ignored bots' text sentiment features, and it is hard to detect social bot just based on contents. This paper proposes a malicious social bot detection method that combines sentiment features in response to this problem. It trains a Bidirectional Long Short-Term Memory model(Bi-LSTM) with an Attention Mechanism to perform sentiment calculation on the online text information of social accounts and analyze the sentiment fluctuations of accounts to get the new sentiment features; Then, it inputs the new features combined with metadata features into different machine learning models for analysis and comparison. Through this method, different machine learning detection models have improved the detection accuracy after combining sentiment features.

Automated summary

Social bots, which exist widely in major social networks, can be maliciously used to manipulate public opinion, steal user privacy, and spread rumors, posing a serious security threat. This paper proposes a method for detecting malicious social bots by combining sentiment features. It utilizes a Bidirectional Long Short-Term Memory model with an Attention Mechanism to perform sentiment analysis on the online text of social accounts, and analyzes the sentiment fluctuations to derive new features. The new features, along with metadata features, are then input into different machine learning models for analysis and comparison, resulting in improved detection accuracy.