G2TT
来源类型Report
规范类型报告
DOIhttps://doi.org/10.7249/RR-A676-1
来源IDRR-A676-1
Detecting Conspiracy Theories on Social Media: Improving Machine Learning to Detect and Understand Online Conspiracy Theories
William Marcellino; Todd C. Helmus; Joshua Kerrigan; Hilary Reininger; Rouslan I. Karimov; Rebecca Ann Lawrence
发表日期2021-04-29
出版年2021
语种英语
结论
  • The hybrid ML model improved conspiracy topic detection.
  • The hybrid ML model dramatically improved on either single model's ability to detect conspiratorial language.
  • Hybrid models likely have broad application to detecting any kind of harmful speech, not just that related to conspiracy theories.
  • Some conspiracy theories, though harmful, rhetorically invoke legitimate social goods, such as health and safety.
  • Some conspiracy theories rhetorically function by creating hate-based "us versus them" social oppositions.
  • Direct contradiction or mockery is unlikely to change conspiracy theory adherence.
摘要

Conspiracy theories circulated online via social media contribute to a shift in public discourse away from facts and analysis and can contribute to direct public harm. Social media platforms face a difficult technical and policy challenge in trying to mitigate harm from online conspiracy theory language. As part of Google's Jigsaw unit's effort to confront emerging threats and incubate new technology to help create a safer world, RAND researchers conducted a modeling effort to improve machine-learning (ML) technology for detecting conspiracy theory language. They developed a hybrid model using linguistic and rhetorical theory to boost performance. They also aimed to synthesize existing research on conspiracy theories using new insight from this improved modeling effort. This report describes the results of that effort and offers recommendations to counter the effects of conspiracy theories that are spread online.

目录
  • Chapter One

    Introduction: Detecting and Understanding Online Conspiracy Language

  • Chapter Two

    Making Sense of Conspiracy Theories

  • Chapter Three

    Modeling Conspiracy Theories: A Hybrid Approach

  • Chapter Four

    Conclusion and Recommendations

  • Appendix A

    Data and Methodology

  • Appendix B

    Stance: Text Analysis and Machine Learning

主题Information Operations ; The Internet ; Machine Learning ; Social Media Analysis
URLhttps://www.rand.org/pubs/research_reports/RRA676-1.html
来源智库RAND Corporation (United States)
引用统计
资源类型智库出版物
条目标识符http://119.78.100.153/handle/2XGU8XDN/524433
推荐引用方式
GB/T 7714
William Marcellino,Todd C. Helmus,Joshua Kerrigan,et al. Detecting Conspiracy Theories on Social Media: Improving Machine Learning to Detect and Understand Online Conspiracy Theories. 2021.
条目包含的文件
文件名称/大小 资源类型 版本类型 开放类型 使用许可
RAND_RRA676-1.pdf(968KB)智库出版物 限制开放CC BY-NC-SA浏览
1640181477042.jpg(6KB)智库出版物 限制开放CC BY-NC-SA缩略图
浏览
个性服务
推荐该条目
保存到收藏夹
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[William Marcellino]的文章
[Todd C. Helmus]的文章
[Joshua Kerrigan]的文章
百度学术
百度学术中相似的文章
[William Marcellino]的文章
[Todd C. Helmus]的文章
[Joshua Kerrigan]的文章
必应学术
必应学术中相似的文章
[William Marcellino]的文章
[Todd C. Helmus]的文章
[Joshua Kerrigan]的文章
相关权益政策
暂无数据
收藏/分享
文件名: RAND_RRA676-1.pdf
格式: Adobe PDF
此文件暂不支持浏览
文件名: 1640181477042.jpg
格式: JPEG

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。