CLMar 13, 2023

MetaTroll: Few-shot Detection of State-Sponsored Trolls with Transformer Adapters

arXiv:2303.07354v116 citationsh-index: 36Has Code
Originality Incremental advance
AI Analysis

This addresses the challenge of combating misinformation by enabling efficient adaptation to new troll campaigns, though it is incremental in building on meta-learning and adapter techniques.

The paper tackles the problem of detecting state-sponsored trolls in novel influence campaigns with limited labeled data, achieving substantial performance improvements over existing few-shot text classification models.

State-sponsored trolls are the main actors of influence campaigns on social media and automatic troll detection is important to combat misinformation at scale. Existing troll detection models are developed based on training data for known campaigns (e.g.\ the influence campaign by Russia's Internet Research Agency on the 2016 US Election), and they fall short when dealing with {\em novel} campaigns with new targets. We propose MetaTroll, a text-based troll detection model based on the meta-learning framework that enables high portability and parameter-efficient adaptation to new campaigns using only a handful of labelled samples for few-shot transfer. We introduce \textit{campaign-specific} transformer adapters to MetaTroll to ``memorise'' campaign-specific knowledge so as to tackle catastrophic forgetting, where a model ``forgets'' how to detect trolls from older campaigns due to continual adaptation. Our experiments demonstrate that MetaTroll substantially outperforms baselines and state-of-the-art few-shot text classification models. Lastly, we explore simple approaches to extend MetaTroll to multilingual and multimodal detection. Source code for MetaTroll is available at: https://github.com/ltian678/metatroll-code.git.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes