A Systematic Survey on Android API Usage for Data-Driven Analytics with Smartphones

TL;DR

This paper systematically reviews how Android APIs, especially Usage Statistics and Accessibility Service APIs, are used in data-driven smartphone research, highlighting trends, limitations, and future directions.

Contribution

It categorizes and analyzes existing research on Android API usage for data-driven analytics, providing a structured overview and identifying key challenges and future research avenues.

Findings

Identification of research themes and data classification structure.

Analysis of data usage trends across research purposes.

Discussion of limitations like API version changes and privacy issues.

Abstract

Recent industrial and academic research has focused on data-driven analytics with smartphones by collecting user interaction, context, and device systems data through Application Programming interfaces (APIs) and sensors. The Android OS provides various APIs to collect such mobile usage and sensor data for third-party developers. Usage Statistics API (US API) and Accessibility Service API (AS API) are representative Android APIs for collecting app usage data and are used for various research purposes as they can collect fine-grained interaction data (e.g., app usage history, user interaction type). Furthermore, other sensor APIs help to collect a user's context and device state data, along with AS/US APIs. This review investigates mobile usage and sensor data-driven research using AS/US APIs, by categorizing the research purposes and the data types. In this paper, the surveyed studies are classified as follows: five themes and 21 subthemes, and a four-layer hierarchical data classification structure. This allows us to identify a data usage trend and derive insight into data collection according to research purposes. Several limitations and future research directions of mobile usage and sensor data-driven analytics research are discussed, including the impact of changes in the Android API versions on research, the privacy and data quality issues, and the mitigation of reproducibility risks with standardized data typology.