Deep Neural Networks for Bot Detection

By Sneha Kudugunta, Emilio Ferrara. Information Sciences, 2018

509 citations recorded by the source corpus.

Abstract The problem of detecting bots, automated social media accounts governed by software but disguising as human users, has strong implications. For example, bots have been used to sway political elections by distorting online discourse, to manipulate the stock market, or to push anti-vaccine conspiracy theories that may have caused health epidemics. Most techniques proposed to date detect bots at the account level, by processing large amounts of social media posts, and leveraging information from network structure, temporal dynamics, sentiment analysis, etc. In this paper, we propose a deep neural network based on contextual long short-term memory (LSTM) architecture that exploits both content and metadata to detect bots at the tweet level: contextual features are extracted from user metadata and fed as auxiliary input to LSTM deep nets processing the tweet text. Another contribution that we make is proposing a technique based on synthetic minority oversampling to generate a large labeled dataset, suitable for deep nets training, from a minimal amount of labeled data (roughly 3000 examples of sophisticated Twitter bots). We demonstrate that, from just one single tweet, our architecture can achieve high classification accuracy (AUC  >  96%) in separating bots from humans. We apply the same architecture to account-level bot detection, achieving nearly perfect classification accuracy (AUC  >  99%). Our system outperforms previous state of the art while leveraging a small and interpretable set of features, yet requiring minimal training data.

Subfields: Information Systems, Sociology and Political Science, Signal Processing

View Paper: https://www.semanticscholar.org/paper/24f0e5dea2c8e017a297117579edd83fd86cf695

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Systems

In Sociology and Political Science

In Signal Processing

Citations in the corpus

Arming the public with artificial intelligence to counter social bots (2019, background): “Recently, Kudugunta and Ferrara (2018) proposed a deep neural network approach based on the contextual long short-term memory (LSTM) architecture that exploits content and metadata to detect bots at the tweet level.”
Characterizing the 2016 Russian IRA influence campaign (2018, methodology): “ll on the liberal/conservative center as well. 3.3 Bot Detection Determining whether either a human or a bot controls a social media account has proven a very challenging task Ferrara et al. (2016b); Kudugunta and Ferrara (2018); Subrahmanian et al. (2016). We use 5 We use the algorithm in the Pytho”
Scalable and Generalizable Social Bot Detection through Data Selection (2019, methodology): “Some methods include information from tweet content in addition to the metadata to detect bots at the tweet level (Kudugunta and Ferrara 2018).”
Finding and Characterizing Information Warfare Campaigns (2020, methodology): “The supervised machine learning models used for bot detection include Naı̈ve Bayes [64], Meta-based [149], SVM [151], and Neural Network [144].”
A Survey on Computational Propaganda Detection (2020, methodology): “Widely used algorithms include decision trees and random forests, SVMs, boosting and bagging (e.g., Adaptive Boost and Decorate) and, more recently, deep neural networks [ Kudugunta and Ferrara, 2018 ] .”