liwca.datasets.dictionaries.fetch_psychnorms

liwca.datasets.dictionaries.fetch_psychnorms(stem)

Fetch one lexicon column from psychNorms as a weighted dictionary.

The psychNorms metabase aggregates 290+ psycholinguistic norms for ~107,000 words across 27 semantic categories (frequency, valence, arousal, concreteness, sensory ratings, etc.). This fetcher downloads psychnorms.zip once and slices the requested column into a single-category weighted .dicx cached at the dictionaries cache root.

Parameters:

stem (str) – Name of the psychNorms norm to extract (case-insensitive). psychNorms columns are already lowercase snake_case, so the stem usually matches the column name verbatim (e.g. "concreteness_brysbaert"). See list_psychnorms_stems for valid names, or liwca.datasets.tables.fetch_psychnorms for the classification metadata.

Returns:

• pandas.DataFrame – Weighted dictionary with one column named after the psychNorms norm and a lowercase DicTerm index.

• If used, cite

• Hussain et al., 2024.

• Probing the contents of semantic representations from text, behavior, and

• brain data using the psychNorms metabase. *arXiv*

• doi (10.48550/arXiv.2412.04936)

Return type:

DataFrame

Examples

>>> from liwca.datasets import dictionaries
>>> dx = dictionaries.fetch_psychnorms("concreteness_brysbaert")