/next-word

Word prediction algorithm created for the Johns Hopkins University Data Science Specialization on Coursera capstone project. Includes code for processing a corpus, building ngram tables, building a GloVe model, and creating a Shiny web app to showcase the algorithm.

Primary LanguageR

next-word

Capstone project for Johns Hopkins University Data Science Specialization on Coursera. I intend to continue developing this for fun after the course is over. Feel free to collaborate if you like.

The repo contains some code used to build an LDA topic model and run it against ngram tables, but I have abandoned that path in favour of trying to use a GloVe word vector model.