Shaping China's national image in a cross-cultural context: sentiment analysis and topic modeling of Bilibili tourists' comments

The subject of this study is the analysis of the impact of social media, namely the Bilibili platform on the perception of China (especially by foreign tourists). The authors of the article analyze in detail the comments of users about the image of China to the tourist videos on this resource. The purpose of the study is to identify the main public perceptions of Chinese culture, the processes of modernization of original China, and the country's infrastructure. The article analyzes through thematic modeling the numerous emotional reactions of users of the Bilibili platform, their feedback about the host country, the choice of topics for discussion and their frequency, responses, etc. Key topics for users of the platform include: admiration for China's urban development, high-speed railways and natural landscapes, as well as criticism of its political system and infrastructure. The latent Dirichlet distribution model is used as a research methodology to determine the topic and the Vader sentiment analysis tool to analyze emotional reactions (neutral/negative/positive). The algorithm of the research methodology includes several stages: data collection (about 9 thousand comments), data purification from unnecessary information, modeling, assessment of the quality of the model used and assessment of emotional coloring. The scientific novelty of the research is due to the analysis of data from one of the largest social networks Bilibili, a comprehensive methodology, and the use of digital diplomacy strategies (shaping the country's image through digital communication). The findings of the study indicate a predominantly positive attitude towards China's national image: 60.7% of comments express a positive opinion, 27.9% – neutral and 11.4% – negative. The authors of the article conclude that social media plays an essential role in the process of forming a positive image of China, especially given the enormous popularity of China among foreigners as a tourist destination, a keen interest in the distinctive Chinese culture and at the same time the innovative infrastructure of the country. Undoubtedly, the conducted research has some limitations (one platform, cultural limitations of the user audience, insufficiency in demographic characteristics and in the sample, the potential for systematic error, etc.). At the same time, these factors determine the scientific potential and importance in shaping a larger-scale media image of China among the digital audience of other countries.

Authors

Institutions

Publication Details

Journal
Litera
Published
2025-05-01
DOI
https://doi.org/10.25136/2409-8698.2025.5.74116
Primary Topic
Sentiment Analysis and Opinion Mining
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Shaping China's national image in a cross-cultural context: sentiment analysis and topic modeling of Bilibili tourists' comments

Yang Ju, Liujiang Ye, Bella A. Bulgarova, Chaochao Han
Litera
Sentiment Analysis and Opinion Mining
article

Shaping China's national image in a cross-cultural context: sentiment analysis and topic modeling of Bilibili tourists' comments

Yang Ju, Liujiang Ye, Bella A. Bulgarova, Chaochao Han
article en

Abstract

The subject of this study is the analysis of the impact of social media, namely the Bilibili platform on the perception of China (especially by foreign tourists). The authors of the article analyze in detail the comments of users about the image of China to the tourist videos on this resource. The purpose of the study is to identify the main public perceptions of Chinese culture, the processes of modernization of original China, and the country's infrastructure. The article analyzes through thematic modeling the numerous emotional reactions of users of the Bilibili platform, their feedback about the host country, the choice of topics for discussion and their frequency, responses, etc. Key topics for users of the platform include: admiration for China's urban development, high-speed railways and natural landscapes, as well as criticism of its political system and infrastructure. The latent Dirichlet distribution model is used as a research methodology to determine the topic and the Vader sentiment analysis tool to analyze emotional reactions (neutral/negative/positive). The algorithm of the research methodology includes several stages: data collection (about 9 thousand comments), data purification from unnecessary information, modeling, assessment of the quality of the model used and assessment of emotional coloring. The scientific novelty of the research is due to the analysis of data from one of the largest social networks Bilibili, a comprehensive methodology, and the use of digital diplomacy strategies (shaping the country's image through digital communication). The findings of the study indicate a predominantly positive attitude towards China's national image: 60.7% of comments express a positive opinion, 27.9% – neutral and 11.4% – negative. The authors of the article conclude that social media plays an essential role in the process of forming a positive image of China, especially given the enormous popularity of China among foreigners as a tourist destination, a keen interest in the distinctive Chinese culture and at the same time the innovative infrastructure of the country. Undoubtedly, the conducted research has some limitations (one platform, cultural limitations of the user audience, insufficiency in demographic characteristics and in the sample, the potential for systematic error, etc.). At the same time, these factors determine the scientific potential and importance in shaping a larger-scale media image of China among the digital audience of other countries.

Litera(5)
Odesa I. I. Mechnikov National University (UA)
Openalex Percentile: Top 91%
Sentiment Analysis and Opinion Mining
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.