NSF Award
1551004
While smart phones provide an excellent way for communication, entertaining and education, they also raise many privacy and security concerns. Children are facing the risks of being exposed to inappropriate content due to mis-rated Apps. Both Android and iOS apps come with maturity ratings that examine the existence and intensity of mature themes within each app. However, each mobile platform adopts its own rating policy and rating strategy which creates inconsistency and inaccurate ratings. The maturity ratings for Android apps are purely a result of app developers' self-report. Many claim that the Android rating policy is unclear, and it is difficult for developers to understand. A more critical risk resides in in-app advertisements. Many apps, especially the free ones, are connected to third party advertisements. Neither mobile platforms nor advertising networks apply these maturity policies to restrict the contents of in-app advertisements. However, this phenomenon has not been studied, nor have the factors that may lead to untruthful maturity ratings been explored. Thus, the risks associated with content inappropriateness are unknown. This project develops mechanisms to compare, analyze and verify the maturity ratings of mobile apps and in-app advertisements, and investigates possible reasons behind the inaccurate ratings. A variety of data will be collected to support the analysis including Web data crawled from the Web, App data from decompiled app code, and advertisement data collected in a number of "demo apps."<br/><br/><br/>This project adopts a multi-disciplinary approach to compare and understand the maturity rating policy difference among different platforms. It plans to investigate the current maturity rating framework on Android, iOS and other third-party authorities such as ESRB. By comparing the same app that appears on both Android and iOS app ratings, the project studies if ratings are reflected in app descriptions, user reviews, developer information, etc. App log data will be collected to analyze content maturity of in-app advertisements. The project will then build an effective text mining approach to estimate the true rating of an app. Using this as a foundation, the project will further analyze and evaluate a large number of Android and iOS app ratings as well as in-app advertisement content. Statistical analysis will be performed to understand the factors that lead to mis-rated maturity ratings.
