[论文] TikStance: A Multimodal and Hierarchical Dataset for Multi-target...

论文概要

研究领域: NLP 作者: Yazhi Zhang, Fuqiang Niu, Bowen Zhang 发布时间: 2025-07-16 arXiv: 2507.12492

中文摘要

政治话语已日益转向短视频平台，但此类内容的计算分析仍受限于同时保留视听信息和层级对话的数据集稀缺。本文提出 TikStance——一个多模态且具备上下文感知的数据集，包含来自TikTok的161个视频和13,876条评论，专为政治讨论中的立场检测而设计。数据集涵盖2024年美国选举周期的三位主要政治人物——唐纳德·特朗普、乔·拜登和卡玛拉·哈里斯——内容收集于2023年9月至2025年1月。每个讨论单元将主视频及其元数据与父链接评论树关联，支持在视听和对话双重上下文中的立场分析。每个条目由三位标注员独立使用三分类方案（支持、反对、中立）进行视频-目标和评论-目标立场标注；存在分歧的条目进行重新标注，最终 Trump、Biden 和 Harris 子集的 Krippendorff's alpha 分别达到0.743、0.723和0.722。描述性分析进一步揭示目标依赖的立场分布差异和对话深度差异，嵌套回复占所有评论的23.3%。通过结合多目标覆盖、层级对话和可靠的多层人工标注，TikStance 支持多模态立场检测、政治传播、计算社会科学和上下文感知自然语言处理研究。

原文摘要

Political discourse has increasingly moved to short-video platforms, yet computational analysis of such content remains constrained by the scarcity of datasets that jointly preserve audiovisual information and hierarchical conversations. Here we present TikStance, a multimodal and context-aware dataset comprising 161 videos and 13,876 comments from TikTok, designed for stance detection in political discussions. The dataset covers three major political figures in the 2024 U.S. election cycle--Donald Trump, Joe Biden, and Kamala Harris--with content collected between September 2023 and January 2025. Each discussion unit links a host video and its metadata to a parent-linked comment tree, enabling stance analysis within both audiovisual and conversational context. Each item was independently labeled by three annotators using a three-class scheme (Favor, Against, None) for video-to-target an...

--- *自动采集于 2026-07-19*

#论文 #arXiv #NLP #小凯