@inproceedings{wang-etal-2026-personatrace,
    title = "{P}ersona{T}race: Synthesizing Realistic Digital Footprints with {LLM} Agents",
    author = "Wang, Minjia  and
      Wang, Yunfeng  and
      Ma, Xiao  and
      Lv, Dexin  and
      Guo, Qifan  and
      Zheng, Lynn  and
      Wang, Benliang  and
      Wang, Lei  and
      Li, Jiannan  and
      Xing, Yongwei  and
      Xu, Junzhe  and
      Sun, Zheng",
    editor = {Matusevych, Yevgen  and
      Eryi{\u{g}}it, G{\"u}l{\c{s}}en  and
      Aletras, Nikolaos},
    booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 5: Industry Track)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.eacl-industry.5/",
    pages = "60--77",
    ISBN = "979-8-89176-384-5",
    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."
}