用AI生成数据训练模型，自动识别用户对AI应用权限的担忧。
Analysing User Reviews to Identify User Concerns Around Permissions in AI Apps
- 用AI生成的安全评论筛选真实用户评论，避免人工标注。
- 模型准确率82%，能有效分类与权限相关的用户反馈。
- 用户更关注对应用的信任感，而非具体权限类型，适合开发者参考。
人工智能正日益融入日常软件，其在移动应用中的集成已成为必然。然而，部分AI应用开发者缺乏安全与隐私最佳实践知识，导致用户需自行监控自身安全并理解数据使用方式。应用评论记录了真实的用户体验，有助于他人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。由于用户评论属于非结构化文本，构建传统标注训练集较为困难。为此，研究利用AI生成的安全与权限相关评论，从大规模人类撰写评论中识别出相关训练样本，无需人工标注。所提方法在权限类评论分类上达到82%的准确率。分析表明，用户更倾向于基于对应用的整体情感态度组织其担忧，而非特定权限类型，这对用户、开发者及平台管理者均有重要启示。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。