Scholarlink

<p>False information can spread quickly on social media, negatively influencing the citizens’ behaviors and responses to social events. To better detect all of the fake news, especially long texts which are harder to find completely, a Long-Text Chinese Rumor detection dataset named LTCR is proposed. The LTCR dataset provides a valuable resource for accurately detecting misinformation, especially in the context of complex fake news related to COVID-19. The dataset consists of 1729 and 561 pieces of real and fake news, respectively. The average lengths of real and fake news are approximately 230 and 152 characters. We also propose DoubleCheck, Salience-aware Fake News Detection Model, which achieves the highest accuracy (95.85%), fake news recall (90.91%) and F-score (90.60%) on the dataset (<a href="https://github.com/Enderfga/DoubleCheck.">https://github.com/Enderfga/DoubleCheck.</a>). </p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

LTCR: Long-Text Chinese Rumor detection dataset

  • 期刊论文

  • 发表日期：

    2025年5月20日

查看全文
  • Ziyang Ma,
  • Mengsha Liu,
  • Guian Fang,
  • Ying Shen

摘要

False information can spread quickly on social media, negatively influencing the citizens’ behaviors and responses to social events. To better detect all of the fake news, especially long texts which are harder to find completely, a Long-Text Chinese Rumor detection dataset named LTCR is proposed. The LTCR dataset provides a valuable resource for accurately detecting misinformation, especially in the context of complex fake news related to COVID-19. The dataset consists of 1729 and 561 pieces of real and fake news, respectively. The average lengths of real and fake news are approximately 230 and 152 characters. We also propose DoubleCheck, Salience-aware Fake News Detection Model, which achieves the highest accuracy (95.85%), fake news recall (90.91%) and F-score (90.60%) on the dataset (https://github.com/Enderfga/DoubleCheck.).