Cross-Platform Short-Video Diplomacy: Topic and Sentiment Analysis of China-US Relations on Douyin and TikTok

TL;DR

The paper addresses how China–U.S. relations are publicly discussed on platform‑specific short‑video ecosystems (Douyin and TikTok) across regulatory and cultural contexts. It employs a mixed‑methods pipeline using BERTopic for topic clustering, large‑language model–driven sentiment labeling, and an ordered logistic regression to link sentiment to provincial socioeconomic indicators, guided by a four‑theory framework (Power Transition, Complex Interdependence, Constructivism, Global Governance). Key findings show Chinese comments are more negative toward the U.S., U.S. comments emphasize constructivist themes, and topics cluster around Economic Strength, Technological Interdependence, Culture, and Global Governance; regional development and internet penetration mitigate negativity. The study demonstrates how platform design and regional context shape online public diplomacy, offering actionable insights for policymakers and highlighting the value of cross‑platform, regionally aware sentiment analyses in understanding Sino‑American public discourse.

Abstract

We examine discussions surrounding China-U.S. relations on the Chinese and American social media platforms \textit{Douyin} and \textit{TikTok}. Both platforms, owned by \textit{ByteDance}, operate under different regulatory and cultural environments, providing a unique perspective for analyzing China-U.S. public discourse. This study analyzed 4,040 videos and 338,209 user comments to assess the public discussions and sentiments on social media regarding China-U.S. relations. Through topic clustering and sentiment analysis, we identified key themes, including economic strength, technological and industrial interdependence, cultural cognition and value pursuits, and responses to global challenges. There are significant emotional differences between China and the US on various themes. Since April 2022, the Chinese government has implemented a new regulation requiring all social media accounts to disclose their provincial-level geolocation information. Utilizing this publicly available data, along with factors such as GDP per capita, minority index, and internet penetration rate, we investigate the changes in sentiment towards the U.S. in mainland China. This study links socioeconomic indicators with online discussions, deeply analyzing how regional and economic factors influence Chinese comments on their views of the US, providing important insights for China-U.S. relationship research and policy making.

Figures (5)

• Figure 1: Word cloud map of (we translated the Chinese into English for display) (1) China; (2) U.S..
• Figure 2: China-U.S. comments by sentiment (negative, positive, neutral) within four theoretical frameworks: (1) China’s comments on the U.S. (2) U.S. Comments on China.
• Figure 3: The levels of negative sentiment expressed by China and the U.S. towards each other are as follows: (1) China's overall negative sentiment, (2) China's hate sentiment, (3) China's criticism or complaints, (4) U.S. overall negative sentiment, (5) U.S. hate sentiment, and (6) U.S. criticism or complaints.
• Figure 4: The levels of negative, positive, and neutral sentiment towards the U.S. across different provinces in China: (1) Negative. (2) Positive. (3) Neutral.
• Figure 5: Word cloud map of (we translated the Chinese into English for display) (1) Power Transition Theory - 7 words in China; (2) Complex Interdependence Theory - 4 words in China; (3) Constructivism - 5 words in China; (4) Global Governance Theory - 5 words in China; (5) Power Transition Theory - 7 words in U.S.; (6) Complex Interdependence Theory - 4 words in U.S.; (7) Constructivism - 5 words in U.S.; (8) Global Governance Theory - 5 words in U.S..