# Detection of Novel Social Bots by Ensembles of Specialized Classifiers

arXiv: https://arxiv.org/abs/2006.06867 · HTML: https://mlsanity.com/paper/2006.06867/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jun 2020.

## Built on by (most cited first, 30 of 32)

- [Anatomy of an AI-powered malicious social botnet](https://mlsanity.com/paper/2307.16336/) (2023)
- [Characteristics and prevalence of fake social media profiles with AI-generated faces](https://mlsanity.com/paper/2401.02627/) (2024)
- [Simplistic Collection and Labeling Practices Limit the Utility of Benchmark Datasets for Twitter Bot Detection](https://mlsanity.com/paper/2301.07015/) (2023)
- [The Spread of Propaganda by Coordinated Communities on Social Media](https://mlsanity.com/paper/2109.13046/) (2021)
- ["This is Fake! Shared it by Mistake": Assessing the Intent of Fake News Spreaders](https://mlsanity.com/paper/2202.04752/) (2022)
- [COVID-19 Vaccine Misinformation Campaigns and Social Media Narratives](https://mlsanity.com/paper/2106.08423/) (2021)
- [Demystifying Misconceptions in Social Bots Research](https://mlsanity.com/paper/2303.17251/) (2023)
- [Studying Fake News Spreading, Polarisation Dynamics, and Manipulation by Bots: a Tale of Networks and Language](https://mlsanity.com/paper/2109.07909/) (2021)
- [Detecting Political Biases of Named Entities and Hashtags on Twitter](https://mlsanity.com/paper/2209.08110/) (2022)
- [A Multilingual Dataset of COVID-19 Vaccination Attitudes on Twitter](https://mlsanity.com/paper/2206.14619/) (2022)
- [Robust Graph Clustering via Meta Weighting for Noisy Graphs](https://mlsanity.com/paper/2311.00322/) (2023)
- [MCWDST: a Minimum-Cost Weighted Directed Spanning Tree Algorithm for Real-Time Fake News Mitigation in Social Media](https://mlsanity.com/paper/2302.12190/) (2023)
- [Socialbots on Fire: Modeling Adversarial Behaviors of Socialbots via Multi-Agent Hierarchical Reinforcement Learning](https://mlsanity.com/paper/2110.10655/) (2021)
- [Vaccine Discourse on Twitter During the COVID-19 Pandemic](https://mlsanity.com/paper/2207.11521/) (2022)
- [IMCI: Integrate Multi-view Contextual Information for Fact Extraction and Verification](https://mlsanity.com/paper/2208.14001/) (2022)
- [MulBot: Unsupervised Bot Detection Based on Multivariate Time Series](https://mlsanity.com/paper/2209.10361/) (2022)
- [False Information, Bots and Malicious Campaigns: Demystifying Elements of Social Media Manipulations](https://mlsanity.com/paper/2308.12497/) (2023)
- [Incentivizing News Consumption on Social Media Platforms Using Large Language Models and Realistic Bot Accounts](https://mlsanity.com/paper/2403.13362/) (2024)
- [From Online Behaviours to Images: A Novel Approach to Social Bot Detection](https://mlsanity.com/paper/2304.07535/) (2023)
- [Unmasking Social Bots: How Confident Are We?](https://mlsanity.com/paper/2407.13929/) (2024)
- [On the efficacy of old features for the detection of new bots](https://mlsanity.com/paper/2506.19635/) (2025)
- [TRACE-Bot: Detecting Emerging LLM-Driven Social Bots via Implicit Semantic Representations and AIGC-Enhanced Behavioral Patterns](https://mlsanity.com/paper/2604.02147/) (2026)
- [Machine Learning-based Automatic Annotation and Detection of COVID-19 Fake News](https://mlsanity.com/paper/2209.03162/) (2022)
- [Personality Profiling: How informative are social media profiles in predicting personal information?](https://mlsanity.com/paper/2309.13065/) (2023)
- [Certainly Bot Or Not? Trustworthy Social Bot Detection via Robust Multi-Modal Neural Processes](https://mlsanity.com/paper/2503.09626/) (2025)
- [The Anatomy of Conspirators: Unveiling Traits using a Comprehensive Twitter Dataset](https://mlsanity.com/paper/2308.15154/) (2023)
- [BotSSCL: Social Bot Detection with Self-Supervised Contrastive Learning](https://mlsanity.com/paper/2402.03740/) (2024)
- [Limits to Predicting Online Speech Using Large Language Models](https://mlsanity.com/paper/2407.12850/) (2024)
- [Public interest in science or bots? Selective amplification of scientific articles on Twitter](https://mlsanity.com/paper/2410.01842/) (2024)
- [What is a Social Media Bot? A Global Comparison of Bot and Human Characteristics](https://mlsanity.com/paper/2501.00855/) (2025)

## Abstract (arXiv)

Malicious actors create inauthentic social media accounts controlled in part by algorithms, known as social bots, to disseminate misinformation and agitate online discussion. While researchers have developed sophisticated methods to detect abuse, novel bots with diverse behaviors evade detection. We show that different types of bots are characterized by different behavioral features. As a result, supervised learning techniques suffer severe performance deterioration when attempting to detect behaviors not observed in the training data. Moreover, tuning these models to recognize novel bots requires retraining with a significant amount of new annotations, which are expensive to obtain. To address these issues, we propose a new supervised learning method that trains classifiers specialized for each class of bots and combines their decisions through the maximum rule. The ensemble of specialized classifiers (ESC) can better generalize, leading to an average improvement of 56% in F1 score for unseen accounts across datasets. Furthermore, novel bot behaviors are learned with fewer labeled examples during retraining. We deployed ESC in the newest version of Botometer, a popular tool to detect social bots in the wild, with a cross-validation AUC of 0.99.