Automatic detection of influential actors in disinformation networks.
Automatic detection of influential actors in disinformation networks.
复制标题
DOI：
10.1073/pnas.2011216118
复制
发表时间：
2021-01-26
影响因子：
11.1
通讯作者：
Rubin DB
中科院分区：
文献类型：
--
作者：
Smith ST;Kao EK;Mackin ED;Shah DC;Simek O;Rubin DB
将数字通信和社交媒体武器化的敌对影响行动 (IO) 对开放民主国家构成了越来越大的威胁。本文提出了一个系统框架，用于自动检测虚假信息叙述、网络和有影响力的行为者。该框架集成了自然语言处理、机器学习、图形分析和网络因果推理，以量化个体参与者在传播 IO 叙事方面的影响。我们提出了一种分类器，可以以 96% 的准确率、79% 的召回率和 96% AUPRC 检测报告的 IO 帐户，并在为 2017 年法国总统选举收集的真实社交媒体数据和 Twitter 披露的已知 IO 帐户上进行了演示。我们的系统还发现显着的网络社区和高影响力的帐户，这些帐户均得到美国国会报告和调查性新闻的独立证实。数字通信和社交媒体武器化，以大规模、速度和影响力开展虚假信息活动，为识别和打击敌对影响行动 (IO) 带来了新的挑战。本文提出了一个端到端框架，用于自动检测虚假信息叙述、网络和有影响力的行为者。该框架集成了自然语言处理、机器学习、图形分析和网络因果推理方法，以量化个体参与者在传播 IO 叙事中的影响。我们使用 2017 年法国总统选举期间收集的 Twitter 数据集以及 Twitter 在广泛的 IO 活动（2007 年 5 月至 2020 年 2 月）中披露的已知 IO 帐户、超过 50,000 个帐户、17 个国家以及包括巨魔和机器人在内的不同帐户类型，展示了其在现实世界敌对 IO 活动中的能力。我们的系统以 96% 的精确度、79% 的召回率和 96% 的精确召回率 (P-R) 曲线下面积检测 IO 帐户；绘制出显着的网络社区；并发现高影响力的帐户，这些帐户逃脱了基于活动计数和网络中心性的传统影响力统计的镜头。结果得到了来自美国国会报告、调查性新闻和 Twitter 提供的 IO 数据集的已知 IO 账户的独立来源的证实。
Hostile influence operations (IOs) that weaponize digital communications and social media pose a rising threat to open democracies. This paper presents a system framework to automate detection of disinformation narratives, networks, and influential actors. The framework integrates natural language processing, machine learning, graph analytics, and network causal inference to quantify the impact of individual actors in spreading the IO narrative. We present a classifier that detects reported IO accounts with 96% precision, 79% recall, and 96% AUPRC, demonstrated on real social media data collected for the 2017 French presidential election and known IO accounts disclosed by Twitter. Our system also discovers salient network communities and high-impact accounts that are independently corroborated by US Congressional reports and investigative journalism. The weaponization of digital communications and social media to conduct disinformation campaigns at immense scale, speed, and reach presents new challenges to identify and counter hostile influence operations (IOs). This paper presents an end-to-end framework to automate detection of disinformation narratives, networks, and influential actors. The framework integrates natural language processing, machine learning, graph analytics, and a network causal inference approach to quantify the impact of individual actors in spreading IO narratives. We demonstrate its capability on real-world hostile IO campaigns with Twitter datasets collected during the 2017 French presidential elections and known IO accounts disclosed by Twitter over a broad range of IO campaigns (May 2007 to February 2020), over 50,000 accounts, 17 countries, and different account types including both trolls and bots. Our system detects IO accounts with 96% precision, 79% recall, and 96% area-under-the precision-recall (P-R) curve; maps out salient network communities; and discovers high-impact accounts that escape the lens of traditional impact statistics based on activity counts and network centrality. Results are corroborated with independent sources of known IO accounts from US Congressional reports, investigative journalism, and IO datasets provided by Twitter.
登录
查看更多内容
影响因子：
2.4
作者：
Peixoto, Tiago P.
通讯作者：
Peixoto, Tiago P.
DOI：
10.1109/tnse.2018.2823324
发表时间：
2019-07-01
影响因子：
6.6
作者：
Kao, Edward K.;Smith, Steven Thomas;Airoldi, Edoardo M.
通讯作者：
Airoldi, Edoardo M.
DOI：
10.14778/3157794.3157797
发表时间：
2017-11
期刊：
Proceedings of the VLDB Endowment. International Conference on Very Large Data Bases
影响因子：
--
作者：
Ratner A;Bach SH;Ehrenberg H;Fries J;Wu S;Ré C
通讯作者：
Ré C
影响因子：
56.9
作者：
Vosoughi, Soroush;Roy, Deb;Aral, Sinan
通讯作者：
Aral, Sinan
影响因子：
6.8
作者：
King, Gary;Pan, Jennifer;Roberts, Margaret E.
通讯作者：
Roberts, Margaret E.