Mobile App Reviews with Appraisal Theory Sentiment Labels

A collection of mobile app reviews manually labeled for sentiment based on appraisal theory parameters like insightfulness and practical usability. The dataset was created by Ruping Zhang and last updated on June 1, 2026. It is a small dataset of 5.5 KB, stored in an XLS file format.

Use Cases

• Training sentiment classification models based on the High/Low performance labels derived from appraisal theory.
• Analyzing user feedback for specific app features like insightfulness and transparency, as mentioned in the description.
• Benchmarking lightweight transformer models like MobileBERT for real-time sentiment analysis in resource-limited environments.
• Studying the application of Explainable AI (SHAP) methods for validating manual data annotation.

Strengths

• Manual annotation accuracy was ensured using the SHAP method from Explainable AI.
• The proposed model described achieved a mean fold accuracy of 88.63% and ROC AUC of 90.91%.
• Labels are aligned with appraisal theory components (appreciation and judgment), providing a nuanced view beyond simple positive/negative sentiment.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is very small at 5.5 KB, indicating a limited scope of reviews.

Provenance

Source

Ruping Zhang via figshare

Collection Method

Reviews were manually labeled based on performance parameters aligned with appraisal theory.

Freshness

Last updated 2026-06-01 17:52:53; freshness should be verified.