English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

TikStance: A Multimodal Hierarchical Dataset for Multi-target Stance Detection on TikTok Political Videos

Forum topic · 小凯 · 2026-07-19

Summary

TikStance is a multimodal, context-aware dataset for stance detection in political discussions on short-video platforms. It comprises 161 TikTok videos and 13,876 comments covering three major figures of the 2024 U.S. election cycle—Donald Trump, Joe Biden, and Kamala Harris—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 hierarchical conversational contexts. Every item was independently annotated by three annotators with a three-class scheme (Favor, Against, None) for both video-to-target and comment-to-target stance; disputed items were relabeled, yielding Krippendorff's alpha of 0.743 (Trump), 0.723 (Biden), and 0.722 (Harris). Descriptive analysis reveals target-dependent differences in stance distribution and conversational depth, with nested replies accounting for 23.3% of comments. The dataset supports research in multimodal stance detection, political communication, computational social science, and context-aware NLP. Paper: arXiv 2507.12492.

Overview

Field: NLP Authors: Yazhi Zhang, Fuqiang Niu, Bowen Zhang Published: 2025-07-16 arXiv: 2507.12492

Key points

  • Political discourse has increasingly moved to short-video platforms, but computational analysis is constrained by the scarcity of datasets that jointly preserve audiovisual information and hierarchical conversations.
  • TikStance is a multimodal, context-aware dataset of 161 TikTok videos and 13,876 comments designed for stance detection in political discussions.
  • Coverage spans three major political figures of the 2024 U.S. election cycle — Donald Trump, Joe Biden, and Kamala Harris — with content collected from September 2023 to January 2025.
  • Each discussion unit links a host video and its metadata to a parent-linked comment tree, enabling stance analysis in 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 and comment-to-target stance; disputed items were relabeled.
  • Inter-annotator agreement (Krippendorff's alpha): 0.743 for the Trump subset, 0.723 for Biden, and 0.722 for Harris.
  • Descriptive analysis shows target-dependent differences in stance distribution and conversation depth; nested replies account for 23.3% of all comments.
  • With multi-target coverage, hierarchical dialogue, and reliable multi-level human annotation, TikStance supports multimodal stance detection, political communication, computational social science, and context-aware NLP research.

Original abstract (excerpt)

> 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...

Paper link: <https://arxiv.org/abs/2507.12492>

Tags

#stance-detection#multimodal#dataset#tiktok#nlp#political-discourse#computational-social-science#arxiv

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178442252