Review with Security Concern Dataset

This dataset contains user reviews collected from 8,999 popular Android game applications on the Google Play Store, each with more than 10 million downloads. A total of 56,439,878 reviews were gathered to investigate whether user feedback reveals meaningful security concerns.To support supervised learning, 6,502 reviews were manually labeled into three types of security concerns: Data Leakage, Excessive Advertising, and Inexpedient Payment. These labels were used to build a classifier for detecting Review with Security Concern (RSC) using active learning and convolutional neural networks.The dataset is suitable for research on mobile security, user feedback analysis, NLP-based threat discovery, and the relationship between perceived app reputation and underlying security risks.This dataset accompanies the publication \u201cPoster: What Can Review with Security Concern Tell Us before Installing Apps?\u201d (UbiComp 2022).