论文标题

untrue.news:一个新的假故事搜索引擎

Untrue.News: A New Search Engine For Fake Stories

论文作者

Woloszyn, Vinicius, Schaeffer, Felipe, Boniatti, Beliza, Cortes, Eduardo, Mohtaj, Salar, Möller, Sebastian

论文摘要

在本文中,我们演示了不真实的新闻,这是一种用于假故事的新搜索引擎。不真实的新闻易于使用,并提供有用的功能,例如:a)一种多语言选项,结合了来自同一主题或人的不同国家和语言的虚假故事; b)用户隐私保护器,通过采用无偏差排名方案来避免过滤器气泡; c)一个协作平台,促进了打击虚假信息的新工具的开发。不真实的新闻依靠Elasticsearch,这是一种基于Lucene库的新的可扩展分析搜索引擎,可提供接近实时的结果。我们演示了两个关键方案:与政治家有关的第一个 - 寻找不同类型的假故事的类别 - 以及与难民有关的第二个类别 - 显示了多语言工具。不真实新闻的原型可通过http://untrue.news访问

In this paper, we demonstrate Untrue News, a new search engine for fake stories. Untrue News is easy to use and offers useful features such as: a) a multi-language option combining fake stories from different countries and languages around the same subject or person; b) an user privacy protector, avoiding the filter bubble by employing a bias-free ranking scheme; and c) a collaborative platform that fosters the development of new tools for fighting disinformation. Untrue News relies on Elasticsearch, a new scalable analytic search engine based on the Lucene library that provides near real-time results. We demonstrate two key scenarios: the first related to a politician - looking how the categories are shown for different types of fake stories - and a second related to a refugee - showing the multilingual tool. A prototype of Untrue News is accessible via http://untrue.news

扫码加入交流群

加入微信交流群

微信交流群二维码

扫码加入学术交流群,获取更多资源