Propaganda is a form of deceptive narratives that instigate or mislead the
public, usually with a political purpose. In this paper, we aim to identify
propaganda in political news at two fine-grained levels: sentence-level and
token-level. We observe that propaganda content is more likely to be embedded
in sentences that attribute causality or assert contrast to nearby sentences,
as well as seen in opinionated evaluation, speculation and discussions of
future expectation. Hence, we propose to incorporate both local and global
discourse structures for propaganda discovery and construct two teacher models
for identifying PDTB-style discourse relations between nearby sentences and
common discourse roles of sentences in a news article respectively. We further
devise two methods to incorporate the two types of discourse structures for
propaganda identification by either using teacher predicted probabilities as
additional features or soliciting guidance in a knowledge distillation
framework. Experiments on the benchmark dataset demonstrate that leveraging
guidance from discourse structures can significantly improve both precision and
recall of propaganda content identification.

该研究旨在通过在句子级和标记级别上识别政治新闻中的宣传内容，识别宣传在句子中嵌入因果关系或与附近句子形成对比的内容以及意见评价、推测和未来预期，进而建立两个教师模型识别附近句子之间的 PDTB 样式话语关系和新闻文章中句子的常见话语角色，通过使用教师预测的概率作为附加特征或在知识蒸馏框架中寻求指导来整合这两种类型的话语结构进行宣传识别，实验结果显示利用话语结构的指导可以显著提高宣传内容识别的精确度和召回率。

指导细粒度宣传识别的话语结构

Discourse Structures Guided Fine-grained Propaganda Identification

Fact checking can be an effective strategy against misinformation, but its
implementation at scale is impeded by the overwhelming volume of information
online. Recent artificial intelligence (AI) language models have shown
impressive ability in fact-checking tasks, but how humans interact with
fact-checking information provided by these models is unclear. Here we
investigate the impact of fact checks generated by a popular AI model on belief
in, and sharing intent of, political news in a preregistered randomized control
experiment. Although the AI performs reasonably well in debunking false
headlines, we find that it does not significantly affect participants' ability
to discern headline accuracy or share accurate news. However, the AI
fact-checker is harmful in specific cases: it decreases beliefs in true
headlines that it mislabels as false and increases beliefs for false headlines
that it is unsure about. On the positive side, the AI increases sharing intents
for correctly labeled true headlines. When participants are given the option to
view AI fact checks and choose to do so, they are significantly more likely to
share both true and false news but only more likely to believe false news. Our
findings highlight an important source of potential harm stemming from AI
applications and underscore the critical need for policies to prevent or
mitigate such unintended consequences.

人工智能模型在事实检查任务中表现出令人印象深刻的能力，但该研究发现，AI 事实检查在一些特定情况下会对人们的信念和新闻共享意图造成有害影响，这凸显出了 AI 应用潜在危害性并强调了预防或减轻此类意外后果的政策的重要性。

人工智能在事实核实方面无效且有潜在危害

Artificial intelligence is ineffective and potentially harmful for fact  checking

The complexity and diversity of today's media landscape provides many
challenges for researchers studying news producers. These producers use many
different strategies to get their message believed by readers through the
writing styles they employ, by repetition across different media sources with
or without attribution, as well as other mechanisms that are yet to be studied
deeply. To better facilitate systematic studies in this area, we present a
large political news data set, containing over 136K news articles, from 92 news
sources, collected over 7 months of 2017. These news sources are carefully
chosen to include well-established and mainstream sources, maliciously fake
sources, satire sources, and hyper-partisan political blogs. In addition to
each article we compute 130 content-based and social media engagement features
drawn from a wide range of literature on political bias, persuasion, and
misinformation. With the release of the data set, we also provide the source
code for feature computation. In this paper, we discuss the first release of
the data set and demonstrate 4 use cases of the data and features: news
characterization, engagement characterization, news attribution and content
copying, and discovering news narratives.

该研究介绍了一个用于研究新闻制作者策略和社交媒体参与度的大型政治新闻数据集，其中包括 136K + 新闻文章和 130 种基于内容和社交媒体的特征。