TWICE: An LLM Agent Framework for Simulating Personalized User Tweeting Behavior with Long-term Temporal Features
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912927455379456 |
|---|---|
| author | Jin, Bingrui Lan, Kunyao Wu, Mengyue |
| author_facet | Jin, Bingrui Lan, Kunyao Wu, Mengyue |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_22222 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TWICE: An LLM Agent Framework for Simulating Personalized User Tweeting Behavior with Long-term Temporal Features Jin, Bingrui Lan, Kunyao Wu, Mengyue Information Retrieval Multiagent Systems 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. |
| title | TWICE: An LLM Agent Framework for Simulating Personalized User Tweeting Behavior with Long-term Temporal Features |
| topic | Information Retrieval Multiagent Systems |
| url | https://arxiv.org/abs/2602.22222 |