论文标题
通过逆增强学习检测巨魔行为：2016年美国大选中俄罗斯巨魔的案例研究
Detecting Troll Behavior via Inverse Reinforcement Learning: A Case Study of Russian Trolls in the 2016 US Election
论文作者
论文摘要
自2016年美国总统大选以来，社交媒体滥用一直引起学术界及其他地区的大规模关注。在操纵运动中，防止和限制用户的恶意活动，例如巨魔和机器人，对于民主，公共卫生等的完整性至关重要。但是，对巨魔帐户的自动检测是一个开放的挑战。在这项工作中，我们提出了一种基于逆增强学习（IRL）捕获巨魔行为并识别巨魔帐户的方法。我们采用IRL来推断一组可能导致用户行为的在线激励措施，这又突出了巨魔和非巨魔帐户之间的行为差异，从而实现了其准确的分类。作为研究案例，我们考虑了美国国会在2016年美国总统大选进行俄罗斯干预期间确定的巨魔帐户。我们报告有希望的结果：基于IRL的方法能够准确检测巨魔帐户（AUC = 89.1％）。两类帐户之间的预测特征的差异使得对反映激励巨魔和非巨魔的独特行为有原则的理解。
Since the 2016 US Presidential election, social media abuse has been eliciting massive concern in the academic community and beyond. Preventing and limiting the malicious activity of users, such as trolls and bots, in their manipulation campaigns is of paramount importance for the integrity of democracy, public health, and more. However, the automated detection of troll accounts is an open challenge. In this work, we propose an approach based on Inverse Reinforcement Learning (IRL) to capture troll behavior and identify troll accounts. We employ IRL to infer a set of online incentives that may steer user behavior, which in turn highlights behavioral differences between troll and non-troll accounts, enabling their accurate classification. As a study case, we consider the troll accounts identified by the US Congress during the investigation of Russian meddling in the 2016 US Presidential election. We report promising results: the IRL-based approach is able to accurately detect troll accounts (AUC=89.1%). The differences in the predictive features between the two classes of accounts enables a principled understanding of the distinctive behaviors reflecting the incentives trolls and non-trolls respond to.
