Bran is a software for corpora linguistic research. It offers statistical algorithms, scraping from social networks and websites, and linguistic tag recognition (Part of Speech, Morphology, Dependencies, Lemmatization) based on the Universal Dependencies format.

It supports many taggers and all the main statistical analisys algoritms. It’s provided with both a graphical user interface and an easy programmable command line interface. The usage of CLI Bran is highly recommended when parsing texts bigger than 500MB, or when the input are multiple files.

Download: https://github.com/zorbaproject/Bran/archive/master.zip

Source code: https://github.com/zorbaproject/Bran