Japanese Twitter Discourse on Traditional Chinese Medicine, 2010–2025

A text corpus of Japanese Twitter data from 2010 to 2025, used to study public perceptions of Traditional Chinese Medicine (TCM). The dataset was created by Shanshan Zhang and employs text mining techniques including BERTopic modeling, sentiment analysis, and co-occurrence network analysis. It was last updated on 2026-05-19.

Use Cases

• Conducting sentiment analysis on public discussions about TCM's clinical efficacy and wellness.
• Performing topic modeling to identify key themes like traditional knowledge, scientific innovation, and business promotion.
• Analyzing co-occurrence networks to understand relationships between topics, sentiment, and user engagement behaviors.
• Studying temporal trends in public sentiment and discourse patterns on social media over a 15-year period.

Strengths

• Covers a 15-year time range from 2010 to 2025, allowing for longitudinal analysis.
• Applies multiple text mining techniques (BERTopic, sentiment analysis, network analysis) as described.
• Released under a permissive CC-BY-4.0 license for reuse.

Limitations

• The dataset is very small at 15.2 KB, suggesting limited textual scope.
• Row count and column-level documentation are unknown, limiting suitability assessment.
• The primary file format is DOCX, which may require conversion for computational analysis.

Provenance

Source

figshare, author Shanshan Zhang.

Collection Method

Text mining of Japanese Twitter data, employing BERTopic modeling, sentiment analysis, and co-occurrence network analysis.

Time Range

2010–2025

Freshness

Last updated 2026-05-19 05:38:33.

Geography

Japan (based on the source of Twitter data).