PersonaTrace: Synthesizing Realistic Digital Footprints with LLM Agents

TL;DR

This paper introduces PersonaTrace, a method that uses large language model agents to generate realistic and diverse digital footprints from user profiles, aiding research and application development.

Contribution

It presents a novel approach for synthesizing digital footprints with LLMs, improving data diversity and realism for behavioral analysis and machine learning.

Findings

Generated data is more diverse and realistic than existing baselines.

Models trained on synthetic data outperform those trained on other synthetic datasets.

Synthetic data enhances performance on real-world out-of-distribution tasks.

Abstract

Digital footprints (records of individuals' interactions with digital systems) are essential for studying behavior, developing personalized applications, and training machine learning models. However, research in this area is often hindered by the scarcity of diverse and accessible data. To address this limitation, we propose a novel method for synthesizing realistic digital footprints using large language model (LLM) agents. Starting from a structured user profile, our approach generates diverse and plausible sequences of user events, ultimately producing corresponding digital artifacts such as emails, messages, calendar entries, reminders, etc. Intrinsic evaluation results demonstrate that the generated dataset is more diverse and realistic than existing baselines. Moreover, models fine-tuned on our synthetic data outperform those trained on other synthetic datasets when evaluated on real-world out-of-distribution tasks.