NLP Model for the Russian National Corpus

Using natural language processing to create a model to classify Russian texts by author's gender.

---

modeling-notebook.ipynb

• Contains exploratory analyses of the Russian National Corpus and the set-up for an LSTM model for classifying by gender

rnc-v4.pickle.zip

• Dictionary version of the downloadable portion of the Russian National Corpus

vector_files folder

• Folder with the TFIDF, CV, LDA, and NMF vectors calculated from my first pass on the RNC texts

ISMT-117-Report.pdf

• Outlining the purpose and preliminary findings of the project