TWICE: An LLM Agent Framework for Simulating Personalized User Tweeting Behavior with Long-term Temporal Features

TL;DR

TWICE is a novel LLM-based framework designed to simulate personalized user tweeting behavior by capturing long-term temporal features and individual styles, improving the realism of user behavior modeling.

Contribution

It introduces a comprehensive framework that integrates personalized profiling, memory modules, and style rewriting to better model long-term social media behavior.

Findings

Enhanced simulation of personalized tweeting behavior

Effective incorporation of long-term temporal dynamics

Improved accuracy in modeling user style changes

Abstract

User simulators are often used to generate large amounts of data for various tasks such as generation, training, and evaluation. However, existing approaches concentrate on collective behaviors or interactive systems, struggling with tasks that require modeling temporal characteristics. To address this limitation, we propose TWICE, an LLM-based framework that leverages the long-term temporal and personalized features of social media data. This framework integrates personalized user profiling, an event-driven memory module, and a workflow for personalized style rewriting, enabling simulation of personalized user tweeting behavior while capturing long-term temporal characteristics. In addition, we conduct a comprehensive evaluation with a focus on analyzing tweeting style and event-based changes in behavior. Experiment results demonstrate that our framework improves personalized user simulation by effectively incorporating temporal dynamics, providing a robust solution for long-term behavior tracking.