Weibo Sentiment Analysis for Urban Planning in Xiamen, 2017

Xiamen, China, is the geographic scope for this dataset of 147,613 Weibo text check-ins from 2017, used to quantify resident sentiments across 1,096 neighborhoods. The dataset was created by Chenjing Fan of Nanjing Forestry University to investigate the multilevel and nonlinear effects of the built environment on public sentiment using regression and gradient boosting models. It provides data support for urban planning and targeted measures to improve living environments.

Use Cases

• Training sentiment analysis models based on Chinese social media text from Weibo.
• Analyzing correlations between urban features like land value and population density with resident sentiment.
• Investigating nonlinear relationships between built environment factors (e.g., security facilities, green space) and public mood.
• Supporting urban policy decisions by quantifying sentiment thresholds for neighborhood planning.

Strengths

• Contains 147,613 individual social media text entries, providing a substantial corpus for analysis.
• Geographically focused on 1,096 neighborhoods within Xiamen, enabling fine-grained urban analysis.
• Based on data from a specific year (2017), allowing for temporal consistency in the study.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.
• Data may reflect geographic and temporal bias inherent to a single city and year from the paperswithcode platform.

Provenance

Source

Chenjing Fan, Nanjing Forestry University, via paperswithcode.

Collection Method

Likely collected via the Weibo API or web scraping of public check-in posts.

Time Range

2017

Geography

Xiamen, China