TikStance: A Multimodal and Hierarchical Dataset for Multi-target Stance Analysis in TikTok Political Conversations

2026-07-16

AI Summary

Existing datasets struggle to simultaneously preserve audiovisual content and hierarchical dialogue structures, limiting fine-grained analysis of political stance expression on short-video platforms. This work introduces a multimodal, context-aware dataset tailored to TikTok political discourse, uniquely integrating video audiovisual features, parent-child comment tree structures, and multi-target ternary stance annotations (support/oppose/neutral). The dataset comprises 161 videos related to the three leading candidates in the 2024 U.S. presidential election and 13,876 associated comments, with human annotations achieving a Krippendorff’s α inter-rater reliability above 0.72. It establishes a high-quality benchmark for multimodal political stance detection and reveals significant differences across political targets in both stance distribution and interaction depth.

Abstract

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 and comment-to-target stance; items with disagreement were re-annotated, and the final Krippendorff's \(α\) reached 0.743, 0.723, and 0.722 for the Trump, Biden, and Harris subsets, respectively. Descriptive analysis further reveals target-dependent differences in stance distributions and conversational depth, with nested replies accounting for 23.3\% of all comments. By combining multi-target coverage, hierarchical conversations, and reliable multi-level human annotations, TikStance supports research in multimodal stance detection, political communication, computational social science, and context-aware natural language processing.

Problem

• stance detection
• multimodal dataset
• hierarchical conversations
• political discourse
• short-video platforms

Innovation

• multimodal stance detection
• hierarchical conversation
• TikTok political discourse
• multi-target stance analysis
• context-aware annotation