Let the Bullets Fly: Multimodal Fake News Detection with Temporal-Aligned Generative Danmaku
作者: Xiansheng Luo, Chaowei Zhang, Zewei Zhang, Yi Zhu, Jipeng Qiang
分类: cs.AI
发布日期: 2026-08-24
💡 一句话要点
提出Genda框架以解决假新闻检测中的时序不一致问题
🎯 匹配领域: 支柱九：具身大模型 (Embodied Foundation Models)
关键词: 假新闻检测 多模态融合 弹幕评论 时序建模 社交信号
📋 核心要点
- 现有假新闻检测方法未能有效处理弹幕评论的累积延迟，影响实时性和准确性。
- 提出Genda框架，通过弹幕触发器和生成器模拟用户反应，生成时序对齐的伪弹幕流。
- DM-FEND模型在中英文假新闻检测基准上表现优异，验证了时序弹幕建模的有效性。
📝 摘要（中文）
社交平台上的弹幕评论可以提供细粒度的社交信号，有助于假新闻检测。然而，弹幕的累积延迟与假新闻检测的实时性需求相悖，导致相关研究不足。为了解决这一问题，本文提出了一种新的时序生成弹幕框架Genda，包含弹幕触发器和弹幕生成器，模拟用户互动过程，生成时序对齐的伪弹幕流。此外，设计了基于弹幕的多模态假新闻检测模型DM-FEND，增强视频、音频、文本和弹幕之间的交互，提升了动态模态对齐和语义噪声抑制。实验结果表明，DM-FEND在中英文基准测试中均优于现有最先进方法，验证了时序弹幕建模在增强鲁棒性和判别能力方面的重要性。
🔬 方法详解
问题定义：本文旨在解决假新闻检测中弹幕评论的累积延迟问题，现有方法未能充分利用弹幕的社交信号，导致实时性不足和检测准确性降低。
核心思路：通过提出Genda框架，模拟用户的互动过程，生成时序对齐的伪弹幕流，以便更好地捕捉用户反应与假新闻之间的关系。
技术框架：Genda框架包括两个主要模块：弹幕触发器用于预测用户反应的时机和强度，弹幕生成器则负责合成相应的语义和情感表达。DM-FEND模型则在此基础上实现多模态假新闻检测。
关键创新：Genda框架的创新在于其时序生成能力，能够生成与用户行为相一致的弹幕流，从而提升假新闻检测的实时性和准确性，与传统方法相比，显著增强了对社交信号的利用。
关键设计：在模型设计中，采用了特定的损失函数来优化弹幕生成的质量，并通过多模态交互机制提高了模型的鲁棒性和判别能力。
🖼️ 关键图片
📊 实验亮点
实验结果显示，DM-FEND模型在FakeSV和FakeTT基准测试中均显著优于现有最先进方法，提升幅度达到XX%（具体数据待补充），验证了时序弹幕建模在假新闻检测中的关键作用。
🎯 应用场景
该研究在社交媒体内容监测、假新闻检测和信息传播分析等领域具有广泛的应用潜力。通过实时捕捉用户反应，能够更有效地识别和应对假新闻，提升信息传播的可信度和安全性，未来可能对社交平台的内容管理和用户体验产生深远影响。
📄 摘要（原文）
The social interactions among crowds via \textit{Danmaku} (a.k.a., bullet comments) on modern multimedia platforms can facilitate both viewpoint conflicts and consensus, providing fine-grained discriminative social signals that can benefit fake news detection. However, the inherent accumulation latency of \textit{Danmaku} in real-world scenarios violates the real-time necessity of fake news detection, making the studies of \textit{Danmaku}-related fake news detection underexplored. To break this violation, we simulate this temporal-aware user interactive process by proposing a novel temporal \textbf{Gen}erative \textbf{da}nmaku framework, called \textbf{Genda}, which consists of: (1) a \textit{Danmaku} Trigger for predicting the timing and intensity of user reactions; and (2) a \textit{Danmaku} Generator for synthesizing corresponding semantic and emotional expressions, thereby mutually constructing a temporally aligned and human-like pseudo \textit{Danmaku} streams. To make the generated \textit{Danmaku} useful for identifying fake news videos, we further design a \textit{Danmaku}-guided Temporal Multimodal fake news detection model - \textbf{DM-FEND}, which enables fine-grained multimodal interactions among video, audio, text, and \textit{Danmaku}, enhancing dynamic modalities alignment and semantic noise inhibition. The experimental results demonstrate that \emph{DM-FEND} consistently outperforms state-of-the-art baselines across both Chinese (FakeSV) and English (FakeTT) benchmarks. Further ablations validate the crucial role of temporal \textit{Danmaku} modeling in enhancing robustness and discriminative capability. Finally, this study offers a bright and robust solution for multimodal fake news detection in modern social interactive fashions by bridging the temporal inconsistency between news and user behaviors.