Information We Can Extract About a User from ‘One Minute Mobile Application Usage’

Understanding human behavior is important and has applications in many domains, such as targeted advertisement, health analytics, security, entertainment, etc. For this purpose, designing a system for activity recognition (AR) is important. However, understanding and analyzing common patterns become challenging since every human can have different behaviors. Since smartphones are easily available to every human being in the modern world, using them to track human activities becomes possible. In this paper, we extracted different human activities using the accelerometer, magnetometer, and gyroscope sensors of android smartphones by building an android mobile application. Using different social media applications, such as Facebook, Instagram, Whatsapp, and Twitter, we extracted the raw sensor values along with the attributes of 29 subjects along with their attributes (class labels) such as age, gender, and left/right/both hands application usage. We extract features from the raw signals and use them to perform classification using different machine learning (ML) algorithms. Using statistical analysis, we show the importance of different features in predicting class labels. Ultimately, we use the trained ML model on our data to extract unknown features from well-known activity recognition data from the UCI repository, highlighting the potential of privacy breaches using ML models. This security analysis could help researchers in the future to take appropriate steps to preserve the privacy of human subjects.