rolling stylometry

[oushiei120]

I am reaching out to recommend the integration of rolling stylometry methods, as outlined in Maciej Eder's "Testing rolling stylometry", into the quanteda package. This approach employs techniques like Rolling SVM, Rolling NSC, and Rolling Delta to analyze textual sequences for stylistic consistency, which could greatly benefit studies on authorship and text complexity.

which can be found in:
rolling_stylometry

[kbenoit]

This would not be added to the core quanteda package but could
a) make an extension package, like the existing stylo, but based on the tokenization methods in quanteda, or
b) incorporate this into quanteda.textmodels.

[oushiei120]

Quanteda is the best text analysis tool in the world. I really hope that Quanteda's workflow can implement rolling stylometry analysis one day