FakeClaim:一个多平台驱动的用于识别2023年巴以冲突相关假新闻的数据集
FakeClaim: A Multiple Platform-driven Dataset for Identification of Fake News on 2023 Israel-Hamas War
AI总结:
本研究发布了首个多平台的2023年以色列-哈马斯战争相关假新闻数据集FakeClaim,涵盖多语言事实核查数据与元数据,并基于文本及评论用预训练模型实现假YouTube视频分类,最佳模型宏F1达87%。
摘要:
我们推出了首个公开可用的数据集,涵盖来自不同平台的事实主张以及与2023年以色列-哈马斯战争相关的虚假YouTube视频,用于自动虚假YouTube视频分类任务。FakeClaim数据集从60家事实核查机构收集,涵盖30种语言,并由受过专业训练的事实核查记者整理,补充了来自事实核查机构的元数据。此外,我们利用文本信息和用户评论,对数据集中的YouTube视频子集开展虚假视频分类研究。我们采用预训练模型,结合不同特征组合对每个视频进行分类。我们性能最佳的微调语言模型Universal Sentence Encoder(USE,通用句子编码器)取得了87%的宏F1值,表明训练后的模型可借助用户讨论区的评论助力揭穿虚假视频。该数据集可在Github获取:https://github.com/Gautamshahi/FakeClaim
英文摘要:
We contribute the first publicly available dataset of factual claims from different platforms and fake YouTube videos on the 2023 Israel-Hamas war for automatic fake YouTube video classification. The FakeClaim data is collected from 60 fact-checking organizations in 30 languages and enriched with metadata from the fact-checking organizations curated by trained journalists specialized in fact-checking. Further, we classify fake videos within the subset of YouTube videos using textual information and user comments. We used a pre-trained model to classify each video with different feature combinations. Our best-performing fine-tuned language model, Universal Sentence Encoder (USE), achieves a Macro F1 of 87\%, which shows that the trained model can be helpful for debunking fake videos using the comments from the user discussion. The dataset is available on Github\footnote{https://github.com/Gautamshahi/FakeClaim}
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。