arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.22977cs.CLcs.AIcs.LG
收藏

DariMis: 为YouTube上的达里语虚假信息检测设计的有害意识建模

DariMis: Harm-Aware Modeling for Dari Misinformation Detection on YouTube

Technical University of Munich, Germany(慕尼黑技术大学);Syiah Kuala University(西亚胡鲁大学);Mainz University of Applied Sciences, Germany(美因茨应用科学大学)

Jawid Ahmad Baktash, Mosa Ebrahimi, Mohammad Zarif Joya, Mursal Dawodi

AI总结:

达里语是阿富汗的主要语言,但缺乏虚假信息检测研究。DariMis是首个手动标注的达里语YouTube视频数据集,包含信息类型和危害等级两个维度,通过分析发现信息类型与危害水平存在结构性关联,并提出双输入编码策略提升虚假信息识别性能。

摘要:

达里语是阿富汗的主要语言,由数千万人使用,但在虚假信息检测文献中仍几乎缺席。我们通过DariMis,首个包含9224个达里语YouTube视频的手动标注数据集,填补这一空白。该数据集在两个维度上进行标注:信息类型(虚假信息、部分真实、真实)和危害等级(低、中、高)。一个关键的实证发现是,这两个维度结构上相互关联,而非独立:55.9%的虚假信息至少具有中等危害潜力,而真实内容中仅有1.0%具有此类潜力。这使得信息类型分类器能够作为隐含危害筛选过滤器在内容审核流程中发挥作用。我们进一步提出了一种双输入编码策略,将视频标题和描述作为独立的BERT段输入,明确建模标题声明与正文内容之间的语义关系,这是误导信息的关键信号。与单一字段拼接的消融研究显示,双输入编码在虚假信息召回率上提升了7.0个百分点(从60.1%提升至67.1%),尽管整体宏F1差异较小(0.09个百分点)。我们将达里/波斯语专用模型(ParsBERT)与XLM-RoBERTa-base进行基准测试;ParsBERT在测试性能上表现最佳,准确率为76.60%,宏F1为72.77%。所有指标均报告了Bootstrap 95%置信区间,并讨论了结果的实用意义和统计局限性。

英文摘要:

Dari, the primary language of Afghanistan, is spoken by tens of millions of people yet remains largely absent from the misinformation detection literature. We address this gap with DariMis, the first manually annotated dataset of 9,224 Dari-language YouTube videos, labeled across two dimensions: Information Type (Misinformation, Partly True, True) and Harm Level (Low, Medium, High). A central empirical finding is that these dimensions are structurally coupled, not independent: 55.9 percent of Misinformation carries at least Medium harm potential, compared with only 1.0 percent of True content. This enables Information Type classifiers to function as implicit harm-triage filters in content moderation pipelines. We further propose a pair-input encoding strategy that represents the video title and description as separate BERT segment inputs, explicitly modeling the semantic relationship between headline claims and body content, a key signal of misleading information. An ablation study against single-field concatenation shows that pair-input encoding yields a 7.0 percentage point gain in Misinformation recall (60.1 percent to 67.1 percent), the safety-critical minority class, despite modest overall macro F1 differences (0.09 percentage points). We benchmark a Dari/Farsi-specialized model (ParsBERT) against XLM-RoBERTa-base; ParsBERT achieves the best test performance with accuracy of 76.60 percent and macro F1 of 72.77 percent. Bootstrap 95 percent confidence intervals are reported for all metrics, and we discuss both the practical significance and statistical limitations of the results.

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。

↑