DfrBrowser 2

Topic modelling is an unsupervised machine learning technique used to scan a large collection of text documents, find hidden semantic structures, and automatically group recurring word patterns into distinct, abstract "topics". You can think of a topic as a cluster of words that frequently occur together in the same context. Each document in the collection is assumed to be a mixture of topics, and each topic is characterized by a distribution of words.

DfrBrowser 2 is a modern, responsive topic modelling browser which provides interactive visualizations and analysis tools for exploring topic models generated by MALLET machine learning package, the most widely used tool for topic modelling by digital humanists.

DFR Browser 2 is a re-imagining of Andrew Goldstone's original dfr-browser. It reproduces all the major functionality of the original, but with an entirely new architecture and additional features for managing bibliographical metadata and assessing topic quality.

DFR Browser 2 is available on GitHub at https://github.com/scottkleinman/dfrbrowser2. A demo can be seen at https://scottkleinman.github.io/dfrbrowser2.