PsychiatryNLPKit.analysis.clause_count

PsychiatryNLPKit.analysis.clause_count(syntax_trees, sections=None)[source]

Average number of clauses per sentence per section.

Notes:

Theoretical basis - Decreased use of words that introduce dependent clauses is predictive of psychosis onset and is related to negative symptoms (Bilgrami et al., 2022).

Args:

syntax_trees: Dict mapping section names to lists of constituency parse: trees.
sections: Sections to process. None processes all sections in: syntax_trees.

Returns:

Dict mapping section names to a dict with key "clause_count". Empty sections receive float("nan").

References:

Bilgrami, Z. R., Sarac, C., Srivastava, A., Herrera, S. N., Azis, M., Haas, S. S., Shaik, R. B., Parvaz, M. A., Mittal, V. A., Cecchi, G., & Corcoran, C. M. (2022). Construct validity for computational linguistic metrics in individuals at clinical risk for psychosis: Associations with clinical ratings. Schizophrenia Research, 245, 90-96. https://doi.org/10.1016/j.schres.2022.01.019