TrustmeWatcher: An Application for Workplace Micro-Sensing and Explainable Well-Being Feedback
Read the original on arXiv Machine Learning →TrustmeWatcher is an application developed for the TRUST‑ME project that integrates OS‑level activity monitoring from ActivityWatch with a user interface for well‑being feedback. It transforms computer‑activity traces into an interactive screen‑time dashboard, synchronizes short questionnaire responses from a StreamDeck, and displays these alongside video highlights. The app uses local AI models to predict six normalized state scores and an overall well‑being score, providing explainable AI insights and privacy controls such as camera and eye‑tracker pause/resume, and has been tested with records from 17 participants.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.