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

arXiv: https://arxiv.org/abs/2411.04691 · HTML: https://mlsanity.com/paper/2411.04691/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 10 references that are in the map.
- First posted on arXiv 7 Nov 2024.

## Builds on (most cited first, 3 of 3)

- [Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Survey](https://mlsanity.com/paper/2402.17944/) (2024)
- [Leveraging LLMs to Predict Affective States via Smartphone Sensor Features](https://mlsanity.com/paper/2407.08240/) (2024)
- [Predicting Affective States from Screen Text Sentiment](https://mlsanity.com/paper/2408.12844/) (2024)

## Built on by (most cited first, 2 of 2)

- [TimeSRL: Generalizable Time-Series Behavioral Modeling via Semantic RL-Tuned LLMs -- A Case Study in Mental Health](https://mlsanity.com/paper/2605.21295/) (2026)
- [Do LLMs Need to See Everything? A Benchmark and Study of Failures in LLM-driven Smartphone Automation using Screentext vs. Screenshots](https://mlsanity.com/paper/2604.17817/) (2026)

## Abstract (arXiv)

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.