PsychiatryNLPKit.analysis.paragraph_level_pseudo_perplexity

PsychiatryNLPKit.analysis.paragraph_level_pseudo_perplexity(data, mask_filling_model, sections=None, manage_lifecycle=True)[source]

Pseudo-perplexity for full paragraphs using a masked language model.

Notes:

Theoretical basis - Pseudo-perplexity estimates perplexity without requiring an autoregressive model, by masking each token and measuring the masked LM’s ability to predict it. Higher perplexity predicts delusion and unusual thought content (He et al., 2024).

Args:

data: Dict mapping section names to raw text strings (from: TextData.data).
mask_filling_model: HFMaskFillingModel instance. Must be loaded: unless manage_lifecycle is True.

sections: Sections to process. None processes all sections in the dict. manage_lifecycle: If True (default), load and unload the model

internally. Set to False when the caller manages the lifecycle.

Returns:

Dict mapping section names to a dict with key "paragraph_level_pseudo_perplexity".

References:

Alqahtani, A., Kayi, E. S., Hamidian, S., Compton, M., & Diab, M. (2022, December). A quantitative and qualitative analysis of schizophrenia language. In A. Lavelli, E. Holderness, A. Jimeno Yepes, A. Minard, J. Pustejovsky, & F. Rinaldi (Eds.), Proceedings of the 13th International Workshop on Health Text Mining and Information Analysis (LOUHI) (pp. 173-183). Association for Computational Linguistics. https://doi.org/10.18653/v1/2022.louhi-1.20 He, R., Palominos, C., Zhang, H., Alonso-Sánchez, M. F., Palaniyappan, L., & Hinzen, W. (2024). Navigating the semantic space: Unraveling the structure of meaning in psychosis using different computational language models. Psychiatry Research, 333, 115752. https://doi.org/10.1016/j.psychres.2024.115752