Improving Experience Sampling with Multi-view User-driven Annotation Prediction

A fundamental challenge in real-time labelling of activity data is user burden. The Experience Sampling Method (ESM) is widely used to obtain such labels for sensor data. However, in an in-situ deployment, it is not feasible to expect users to precisely label the start and end time of each event or activity. For this reason, time-point based experience sampling (without an actual start and end time) is prevalent. We present a framework that applies multi-instance and semi-supervised learning techniques to perform to predict user annotations from multiple mobile sensor data streams. Our proposed framework estimates users' annotations in ESM-based studies progressively, via an interactive pipeline of co-training and active learning. We evaluate our work using data collected from an in-the-wild data collection.