How are your Apps Doing? QoE Inference and Analysis in Mobile Devices

Abstract

Web browsing has become the most important application of the Internet for the end user. When it comes to mobile devices, web services are mainly accessed through apps. This paper tackles the problem of Web Quality of Experience (QoE) in mobile devices, with a specific focus on apps QoE monitoring and analysis, using in-network (encrypted) traffic measurements. Measuring apps QoE is complex, not only from an instrumentation point of view, but also from the heterogeneity of user interactions which might realize substantially different user experience. To this end, we conduct a feasibility study on four specific and popular Android apps and their corresponding web services. Our test automation framework emulates and measures different user interactions commonly executed during an app session, including the app startup, clicking, scrolling, and searching. The resulting traffic is characterized on different dimensions, and machine learning models are trained to identify web services, apps, and user interactions, and to infer their QoE. The proposed models can correctly identify the specific web service and app in 86% of the cases and accurately estimate the associated QoE with small errors. Our preliminary study represents a first step towards an in-network, web QoE monitoring solution for mobile-device apps.

Machine Learning With Computer Networks: Techniques, Datasets, and Models

“…These features are then fed to ML models to learn specific patterns exhibited by different traffic types or services. Beyond traffic classification, this type of analytics is often used for security-related tasks like intrusion detection or fingerprinting of websites, browsers, devices, and operating systems, and for estimating the QoE of services [159], [160]. Due to the prevalence of those topics, there also exists a variety of datasets for the different network traffic analytic tasks.…”

Long-Term Video QoE Assessment Studies: A Systematic Review

“…Multiple papers ( [21], [22], [23], [29], [31]) monitored the user's interaction with YouTube. The studies used the YoMoApp (YouTube Performance Monitoring Application) -which make use of the YouTube mobile website and the YouTube HTML5 API to exactly replicate the YouTube service.…”

“…In papers [21] and [37] the participants were only asked about overall quality on 5-point ACR scale. In papers [22] and [23], the questions included the user's feedback on the quality of the video, the quality of the streaming, the user's opinion on the video content (using ACR scale), as well as the service acceptability (here the possible answers were yes/no). In the study described in the paper [29] participants were asked to rate the overall quality on a 5-point ACR scale and to indicate whether the session quality was acceptable.…”