@inproceedings{zegers-kleinberg-2025-utility,
    title = "The Utility of {LLM} Text Generation in Longitudinal Psychological Datasets",
    author = "Zegers, Jari  and
      Kleinberg, Bennett",
    editor = "Velutharambath, Aswathy  and
      Labat, Sofie  and
      Falk, Neele  and
      Plaza-del-Arco, Flor Miriam  and
      Klinger, Roman  and
      Hoste, V{\'e}ronique",
    booktitle = "Proceedings of the First Workshop on Integrating {NLP} and Psychology to Study Social Interactions ({NLPSI}) @{ICWSM} `25",
    month = jun,
    year = "2025",
    address = "Copenhagen, Denmark",
    publisher = "Association for the Advancement of Artificial Intelligence (www.aaai.org)",
    url = "https://preview.aclanthology.org/ingest-nlpsi/2025.nlpsi-1.10/",
    pages = "92--94",
    abstract = "As part of this ongoing work, we prompted an LLM with three waves of texts from a longitudinal panel dataset to generate a text for wave 4. We compared generated to ground truth texts using cosine similarity on embeddings and tested whether text similarity was associated with psychological variables. We found limited evidence for an association but do find differences in the topics used in generated versus ground-truth texts. An explanation for differences in text similarities remains the subject of ongoing investigation."
}