AWARE Narrator and the Utilization of Large Language Models to Extract Behavioral Insights from Smartphone Sensing Data

TL;DR

This paper introduces AWARE Narrator, a novel framework that converts smartphone sensor data into detailed English narratives, enabling behavioral analysis and mental health insights using large language models.

Contribution

It presents a new method for transforming raw sensor data into structured narratives, enhancing behavioral and psychological state analysis from smartphone sensing data.

Findings

Successfully generated comprehensive activity narratives from sensor data.

Demonstrated potential for behavioral and mental health analysis using language models.

Applied framework to university student data over a week.

Abstract

Smartphones, equipped with an array of sensors, have become valuable tools for personal sensing. Particularly in digital health, smartphones facilitate the tracking of health-related behaviors and contexts, contributing significantly to digital phenotyping, a process where data from digital interactions is analyzed to infer behaviors and assess mental health. Traditional methods process raw sensor data into information features for statistical and machine learning analyses. In this paper, we introduce a novel approach that systematically converts smartphone-collected data into structured, chronological narratives. The AWARE Narrator translates quantitative smartphone sensing data into English language descriptions, forming comprehensive narratives of an individual's activities. We apply the framework to the data collected from university students over a week, demonstrating the potential of utilizing the narratives to summarize individual behavior, and analyzing psychological states by leveraging large language models.