发表机构
College of Technological Innovation, Zayed University; College of Interdisciplinary Studies, Zayed University; University of Adelaide; National University of Computer and Emerging Sciences; School of Computer Science, Taylor’s University; Islamia College University（扎耶德大学技术创新学院; 扎耶德大学跨学科研究学院; 阿德莱德大学; 国家计算机与新兴科学大学; 泰莱大学计算机科学学院; 伊斯兰尼亚学院大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出一种机器学习模型，利用AI生成的评论从人工评论语料库中识别训练样本，将AI应用评论分类为权限相关类别，准确率达82%，发现用户按对应用的情感组织权限关切。
AI 中文摘要
人工智能正日益融入日常软件，使其与移动应用的结合成为必然。然而，AI移动应用开发者并不总是精通安全与隐私最佳实践，导致用户需自行监控安全状况并了解应用如何使用其数据。应用评论记录了真实用户体验，帮助他人在下载前做出明智决策。本文提出一种机器学习模型，用于将AI应用评论分类为与权限相关的类别。由于用户评论是非结构化的，构建传统带标注训练集较为困难。为解决此问题，本文利用AI生成的安全与权限相关评论，从大量人工撰写的评论语料库中识别相关训练样本，无需人工标注。该方法对权限相关评论的分类准确率达82%。分析显示，用户是根据对请求应用的情感而非特定权限类型来组织其关切的，这对用户、开发者及平台管理员均具有启示意义。
英文摘要
Artificial intelligence is increasingly embedded in everyday software, making its integration into mobile apps inevitable. However, AI mobile app developers are not always versed in security and privacy best practices, leaving users to monitor their own security and understand how apps use their data. App reviews capture real user experiences, helping others make informed decisions before downloading. This paper presents a machine learning model for classifying AI app reviews into permission-related categories. Because user reviews are unstructured, assembling a conventional labeled training set is difficult. To address this, AI-generated security and permission reviews are used to identify relevant training examples from a large corpus of human-written reviews, eliminating the need for manual annotation. The proposed approach classified permission reviews with an accuracy of 82%. Analysis shows that users organise their concerns by sentiment toward the requesting app rather than specific permission types, with implications for users, developers, and platform administrators.
Comments10 pages, 2 Figures and 3 Tables
