论文标题
YouTube的DEDADICAL：表征，检测和个性化不宽容的阿拉伯视频
Deradicalizing YouTube: Characterization, Detection, and Personalization of Religiously Intolerant Arabic Videos
论文作者
论文摘要
越来越多的证据表明，YouTube的建议算法通过浮出水面的极端内容在在线激进化中起作用。尤其是激进的伊斯兰团体一直从YouTube的全球吸引力中获利，以传播仇恨和圣战宣传。在这项定量，数据驱动的研究中，我们研究了宗教不宽容的阿拉伯语YouTube视频的普遍性，平台推荐此类视频的趋势以及这些建议如何受到人口统计学和观察历史的影响。根据我们开发的深度学习分类器，旨在检测可恶的视频和大规模的350k视频数据集，我们发现针对宗教少数群体的阿拉伯视频在搜索结果（30％）和第一级建议（21％）（21％）中尤为普遍，而整体捕获的建议点为仇恨视频。我们的个性化审计实验表明，性别和宗教身份可以大大影响暴露于仇恨内容的程度。我们的结果为在线激进化现象提供了重要的见解，并促进了在线有害内容。
Growing evidence suggests that YouTube's recommendation algorithm plays a role in online radicalization via surfacing extreme content. Radical Islamist groups, in particular, have been profiting from the global appeal of YouTube to disseminate hate and jihadist propaganda. In this quantitative, data-driven study, we investigate the prevalence of religiously intolerant Arabic YouTube videos, the tendency of the platform to recommend such videos, and how these recommendations are affected by demographics and watch history. Based on our deep learning classifier developed to detect hateful videos and a large-scale dataset of over 350K videos, we find that Arabic videos targeting religious minorities are particularly prevalent in search results (30%) and first-level recommendations (21%), and that 15% of overall captured recommendations point to hateful videos. Our personalized audit experiments suggest that gender and religious identity can substantially affect the extent of exposure to hateful content. Our results contribute vital insights into the phenomenon of online radicalization and facilitate curbing online harmful content.
