• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

用于简短且有噪声的用户生成数据的迭代主题模型过滤框架：分析推特上的阴谋论

An iterative topic model filtering framework for short and noisy user-generated data: analyzing conspiracy theories on twitter.

作者信息

Kant Gillian, Wiebelt Levin, Weisser Christoph, Kis-Katos Krisztina, Luber Mattias, Säfken Benjamin

机构信息

University of Göttingen, Göttingen, Germany.

Campus-Institut Data Science (CIDAS), University of Göttingen, Göttingen, Germany.

出版信息

Int J Data Sci Anal. 2022 May 6:1-21. doi: 10.1007/s41060-022-00321-4.

DOI:10.1007/s41060-022-00321-4
PMID:35542313
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC9072765/
Abstract

Conspiracy theories have seen a rise in popularity in recent years. Spreading quickly through social media, their disruptive effect can lead to a biased public view on policy decisions and events. We present a novel approach for LDA-pre-processing called Iterative Filtering to study such phenomena based on Twitter data. In combination with Hashtag Pooling as an additional pre-processing step, we are able to achieve a coherent framing of the discussion and topics of interest, despite of the inherent noisiness and sparseness of Twitter data. Our novel approach enables researchers to gain detailed insights into discourses of interest on Twitter, allowing them to identify tweets iteratively that are related to an investigated topic of interest. As an application, we study the dynamics of conspiracy-related topics on US Twitter during the last four months of 2020, which were dominated by the US-Presidential Elections and Covid-19. We monitor the public discourse in the USA with geo-spatial Twitter data to identify conspiracy-related contents by estimating Latent Dirichlet Allocation (LDA) Topic Models. We find that in this period, usual conspiracy-related topics played a marginal role in comparison with dominating topics, such as the US-Presidential Elections or the general discussions about Covid-19. The main conspiracy theories in this period were the ones linked to "Election Fraud" and the "Covid-19-hoax." Conspiracy-related keywords tended to appear together with Trump-related words and words related to his presidential campaign.

摘要

近年来，阴谋论越来越流行。它们通过社交媒体迅速传播，其破坏作用可能导致公众对政策决策和事件产生偏见性看法。我们提出了一种名为迭代过滤的LDA预处理新方法，以基于推特数据研究此类现象。结合标签池化作为额外的预处理步骤，尽管推特数据存在固有的噪声和稀疏性，我们仍能够实现对讨论和感兴趣话题的连贯框架构建。我们的新方法使研究人员能够深入了解推特上感兴趣的话语，使他们能够迭代地识别与所研究的感兴趣话题相关的推文。作为一个应用，我们研究了2020年最后四个月美国推特上与阴谋相关话题的动态，这期间主要受美国总统选举和新冠疫情的影响。我们使用地理空间推特数据监测美国的公众话语，通过估计潜在狄利克雷分配（LDA）主题模型来识别与阴谋相关的内容。我们发现，在此期间，与占主导地位的话题（如美国总统选举或关于新冠疫情的一般讨论）相比，常见的与阴谋相关的话题只起了边缘作用。这一时期的主要阴谋论是与“选举欺诈”和“新冠疫情骗局”相关的理论。与阴谋相关的关键词往往与与特朗普相关的词汇以及与他总统竞选相关的词汇一同出现。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c56c/9072765/9efd0e33dae1/41060_2022_321_Fig19_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c56c/9072765/876381765b0b/41060_2022_321_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c56c/9072765/1ab534413739/41060_2022_321_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c56c/9072765/1b8058de77c4/41060_2022_321_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c56c/9072765/a07728f4dd1e/41060_2022_321_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c56c/9072765/33263ef5c523/41060_2022_321_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c56c/9072765/77d592a6d8f9/41060_2022_321_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c56c/9072765/bd6655c59b1f/41060_2022_321_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c56c/9072765/ca49af271ed8/41060_2022_321_Fig8_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c56c/9072765/077bfcde9003/41060_2022_321_Fig9_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c56c/9072765/e7a87b3e4b50/41060_2022_321_Fig10_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c56c/9072765/778cee20b7be/41060_2022_321_Fig11_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c56c/9072765/7660789ef53d/41060_2022_321_Fig12_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c56c/9072765/0e096ae20792/41060_2022_321_Fig13_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c56c/9072765/080a81fde124/41060_2022_321_Fig14_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c56c/9072765/98fe1a70f56b/41060_2022_321_Fig15_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c56c/9072765/af5b8c3d932b/41060_2022_321_Fig16_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c56c/9072765/a880840be533/41060_2022_321_Fig17_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c56c/9072765/5bdbad783b88/41060_2022_321_Fig18_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c56c/9072765/9efd0e33dae1/41060_2022_321_Fig19_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c56c/9072765/876381765b0b/41060_2022_321_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c56c/9072765/1ab534413739/41060_2022_321_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c56c/9072765/1b8058de77c4/41060_2022_321_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c56c/9072765/a07728f4dd1e/41060_2022_321_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c56c/9072765/33263ef5c523/41060_2022_321_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c56c/9072765/77d592a6d8f9/41060_2022_321_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c56c/9072765/bd6655c59b1f/41060_2022_321_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c56c/9072765/ca49af271ed8/41060_2022_321_Fig8_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c56c/9072765/077bfcde9003/41060_2022_321_Fig9_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c56c/9072765/e7a87b3e4b50/41060_2022_321_Fig10_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c56c/9072765/778cee20b7be/41060_2022_321_Fig11_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c56c/9072765/7660789ef53d/41060_2022_321_Fig12_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c56c/9072765/0e096ae20792/41060_2022_321_Fig13_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c56c/9072765/080a81fde124/41060_2022_321_Fig14_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c56c/9072765/98fe1a70f56b/41060_2022_321_Fig15_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c56c/9072765/af5b8c3d932b/41060_2022_321_Fig16_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c56c/9072765/a880840be533/41060_2022_321_Fig17_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c56c/9072765/5bdbad783b88/41060_2022_321_Fig18_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c56c/9072765/9efd0e33dae1/41060_2022_321_Fig19_HTML.jpg

相似文献

1
An iterative topic model filtering framework for short and noisy user-generated data: analyzing conspiracy theories on twitter.用于简短且有噪声的用户生成数据的迭代主题模型过滤框架：分析推特上的阴谋论
Int J Data Sci Anal. 2022 May 6:1-21. doi: 10.1007/s41060-022-00321-4.
2
COVID-19 and the "Film Your Hospital" Conspiracy Theory: Social Network Analysis of Twitter Data.新冠疫情与“拍摄你的医院”阴谋论：基于推特数据的社交网络分析
J Med Internet Res. 2020 Oct 5;22(10):e22374. doi: 10.2196/22374.
3
COVID-19 and the 5G Conspiracy Theory: Social Network Analysis of Twitter Data.新冠疫情与5G阴谋论：基于推特数据的社交网络分析
J Med Internet Res. 2020 May 6;22(5):e19458. doi: 10.2196/19458.
4
Public Discourse, User Reactions, and Conspiracy Theories on the X Platform About HIV Vaccines: Data Mining and Content Analysis.X 平台上关于 HIV 疫苗的公共话语、用户反应和阴谋论：数据挖掘和内容分析。
J Med Internet Res. 2024 Apr 3;26:e53375. doi: 10.2196/53375.
5
Tweet Topics and Sentiments Relating to COVID-19 Vaccination Among Australian Twitter Users: Machine Learning Analysis.澳大利亚推特用户与 COVID-19 疫苗接种相关的推文主题和情绪：机器学习分析。
J Med Internet Res. 2021 May 19;23(5):e26953. doi: 10.2196/26953.
6
Dynamics of the Negative Discourse Toward COVID-19 Vaccines: Topic Modeling Study and an Annotated Data Set of Twitter Posts.针对 COVID-19 疫苗的负面话语动态：主题建模研究与 Twitter 帖子的标注数据集。
J Med Internet Res. 2023 Apr 12;25:e41319. doi: 10.2196/41319.
7
Cross-platform spread: vaccine-related content, sources, and conspiracy theories in YouTube videos shared in early Twitter COVID-19 conversations.跨平台传播：在早期 Twitter COVID-19 对话中分享的 YouTube 视频中的疫苗相关内容、来源和阴谋论。
Hum Vaccin Immunother. 2022 Dec 31;18(1):1-13. doi: 10.1080/21645515.2021.2003647. Epub 2022 Jan 21.
8
"Thought I'd Share First" and Other Conspiracy Theory Tweets from the COVID-19 Infodemic: Exploratory Study.“我想率先分享”和其他有关 COVID-19 信息疫情的阴谋论推文：探索性研究。
JMIR Public Health Surveill. 2021 Apr 14;7(4):e26527. doi: 10.2196/26527.
9
COCO: an annotated Twitter dataset of COVID-19 conspiracy theories.COCO：一个带有注释的关于新冠病毒阴谋论的推特数据集。
J Comput Soc Sci. 2023 Apr 4:1-42. doi: 10.1007/s42001-023-00200-3.
10
Twitter's Role in Combating the Magnetic Vaccine Conspiracy Theory: Social Network Analysis of Tweets.推特在打击磁性疫苗阴谋论中的作用：推特的社交网络分析
J Med Internet Res. 2023 Mar 31;25:e43497. doi: 10.2196/43497.

引用本文的文献

1
Pseudo-document simulation for comparing LDA, GSDMM and GPM topic models on short and sparse text using Twitter data.使用推特数据进行伪文档模拟，以比较LDA、GSDMM和GPM主题模型在短文本和稀疏文本上的表现。
Comput Stat. 2023;38(2):647-674. doi: 10.1007/s00180-022-01246-z. Epub 2022 Jul 9.

本文引用的文献

1
Unsupervised document classification integrating web scraping, one-class SVM and LDA topic modelling.整合网络爬虫、单类支持向量机和潜在狄利克雷分配主题建模的无监督文档分类
J Appl Stat. 2021 Apr 27;50(3):574-591. doi: 10.1080/02664763.2021.1919063. eCollection 2023.
2
Work from home during the COVID-19 pandemic: An observational study based on a large geo-tagged COVID-19 Twitter dataset (UsaGeoCov19).2019冠状病毒病大流行期间的居家办公：基于一个大型带有地理标签的2019冠状病毒病推特数据集（美国地理新冠19）的观察性研究
Inf Process Manag. 2022 Mar;59(2):102820. doi: 10.1016/j.ipm.2021.102820. Epub 2021 Dec 9.
3
Conspiracy in the time of corona: automatic detection of emerging COVID-19 conspiracy theories in social media and the news.
新冠疫情时期的阴谋论：社交媒体和新闻中新兴的新冠病毒阴谋论自动检测
J Comput Soc Sci. 2020;3(2):279-317. doi: 10.1007/s42001-020-00086-5. Epub 2020 Oct 28.
4
Public Perception of the COVID-19 Pandemic on Twitter: Sentiment Analysis and Topic Modeling Study.公众对 Twitter 上 COVID-19 大流行的看法：情感分析和主题建模研究。
JMIR Public Health Surveill. 2020 Nov 11;6(4):e21978. doi: 10.2196/21978.
5
Public discourse and sentiment during the COVID 19 pandemic: Using Latent Dirichlet Allocation for topic modeling on Twitter.新冠疫情期间的公共话语和情绪：在 Twitter 上使用潜在狄利克雷分配进行主题建模。
PLoS One. 2020 Sep 25;15(9):e0239441. doi: 10.1371/journal.pone.0239441. eCollection 2020.
6
Belief in COVID-19 Conspiracy Theories Reduces Social Distancing over Time.相信新冠病毒阴谋论会随着时间的推移而减少社交距离。
Appl Psychol Health Well Being. 2020 Dec;12(4):1270-1285. doi: 10.1111/aphw.12223. Epub 2020 Aug 30.