理解移动应用评论以指导滥用审计
Understanding Mobile App Reviews to Guide Misuse Audits
AI总结:
本研究利用应用评论构建计算模型,识别可被利用的应用及其滥用功能,经人工验证确认156个应用,提出四种可被利用功能类型,以支持大规模滥用审计。
摘要:
问题:我们解决了负责任计算中的一个挑战,即一个可被利用的移动应用被一个应用用户(滥用者)针对另一个用户或旁观者(受害者)进行滥用。我们引入了应用滥用审计的概念,作为一种无需访问其实现即可确定应用是否可被利用的方法。方法:我们利用应用评论来识别可被利用的应用及其支持滥用的功能。首先,我们构建一个计算模型来识别令人警觉的评论(报告滥用行为)。其次,利用该模型,我们识别可被利用的应用及其功能。第三,我们通过人工检查评论来验证这些发现。发现:滥用者和受害者的叙述大多聚焦于过去的滥用事件,而第三方的叙述则主要识别出表明存在滥用潜力的故事。令人惊讶的是,滥用者发布的正面评论,其语言表现出高度支配性,也揭示了滥用行为。总共,我们确认了156个促进滥用的可被利用应用。基于我们的定性分析,我们发现可被利用的应用表现出四种类型的可被利用功能。意义:我们的方法可以帮助识别可被利用的应用及其功能,从而促进对大量应用的滥用审计。
英文摘要:
Problem: We address the challenge in responsible computing where an exploitable mobile app is misused by one app user (an abuser) against another user or bystander (victim). We introduce the idea of a misuse audit of apps as a way of determining if they are exploitable without access to their implementation. Method: We leverage app reviews to identify exploitable apps and their functionalities that enable misuse. First, we build a computational model to identify alarming reviews (which report misuse). Second, using the model, we identify exploitable apps and their functionalities. Third, we validate them through manual inspection of reviews. Findings: Stories by abusers and victims mostly focus on past misuses, whereas stories by third parties mostly identify stories indicating the potential for misuse. Surprisingly, positive reviews by abusers, which exhibit language with high dominance, also reveal misuses. In total, we confirmed 156 exploitable apps facilitating the misuse. Based on our qualitative analysis, we found exploitable apps exhibiting four types of exploitable functionalities. Implications: Our method can help identify exploitable apps and their functionalities, facilitating misuse audits of a large pool of apps.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。