Useful links

[PythonSemicolon]

Good project structure: https://aicbt.com/authorship-attribution/

Language-independent features: https://aclanthology.org/2021.mtsummit-loresmt.2.pdf

Linguistic features: https://asmp-eurasipjournals.springeropen.com/articles/10.1186/s13636-015-0052-y

Fry readability: https://www.jstor.org/stable/pdf/40018802.pdf?refreqid=fastly-default\%3A3f0933cd87c1d55ae89bf1bdc4df9492&ab\_segments=&origin=&initiator=&acceptTC=1

Stylometric Analysis: https://github.com/Hassaan-Elahi/Writing-Styles-Classification-Using-Stylometric-Analysis

Lexical richness measures: https://languagetestingasia.springeropen.com/articles/10.1186/s40468-021-00133-6

NLTK Sonority sequencing (for syllable parsing): https://www.nltk.org/_modules/nltk/tokenize/sonority_sequencing.html

Cross-Lingual Readability: https://aclanthology.org/2021.nlp4call-1.4.pdf

Syntactic Complexity: https://core.ac.uk/download/pdf/71986629.pdf

Syntactic/Quasi-Syntactic in Stylometry: https://www.ai.uga.edu/sites/default/files/inline-files/hollingsworth_charles_d_201208_ms.pdf

Ideas for Stylometric Features: https://www.researchgate.net/publication/283786326_Stylometry_Metrics_Selection_for_Creating_a_Model_for_Evaluating_the_Writing_Style_of_Authors_According_to_Their_Cultural_Orientation

Justifying our choice of verb density:
https://spaldingmfablog.wordpress.com/2016/08/01/creating-the-illusion-of-action-verb-density-2/
NOTE: The source mentions that Virginia Woolf (who is present in our Spanish data) is characterized by the high verb density.

Lexical Density ratios: https://www.researchgate.net/figure/Distributions-of-lexical-density-by-group-a-noun-ratio-b-verb-ratio-c-adjective_fig2_329888642

ALL CITED

[PythonSemicolon]

don't forget to cite packages used in code (HuggingFace models for POS, syllabification models) - CITED

don't forget to cite actual train/test data (written works) - CITED