YouTube聊天:理解错误信息和政治YouTube视频的在线评论话语
YouTube Chatter: Understanding Online Comments Discourse on Misinformative and Political YouTube Videos
摘要:
我们对YouTube上含有错误信息的政治内容的评论进行了初步分析,并将其与可信或非政治视频的评论进行了比较,并根据媒体偏见事实检查(如适用)对我们频道的偏见和事实评级进行了标记。我们最有趣的发现之一是,特别两极分化或错误信息的政治渠道(左偏,右偏,PragerU,阴谋伪科学和可疑来源)比非政治或亲科学频道产生更多的评论,每次观看的回复数多7.5倍,多10.42倍;特别是,阴谋伪科学和可疑来源比非政治和亲科学频道产生了8.3倍的评论和11.0倍的回复。我们还比较了平均线程长度,平均评论长度和跨渠道的亵渎率,并提出了简单的机器学习分类器,用于基于这些统计数据预测视频的偏见类别。
英文摘要:
We conduct a preliminary analysis of comments on political YouTube content containing misinformation in comparison to comments on trustworthy or apolitical videos, labelling the bias and factual ratings of our channels according to Media Bias Fact Check where applicable. One of our most interesting discoveries is that especially-polarized or misinformative political channels (Left-Bias, Right-Bias, PragerU, Conspiracy-Pseudoscience, and Questionable Source) generate 7.5x more comments per view and 10.42x more replies per view than apolitical or Pro-Science channels; in particular, Conspiracy-Pseudoscience and Questionable Sources generate 8.3x more comments per view and 11.0x more replies per view than apolitical and Pro-Science channels. We also compared average thread lengths, average comment lengths, and profanity rates across channels, and present simple machine learning classifiers for predicting the bias category of a video based on these statistics.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。