Vadim Katsemba
02/17/2017
This application was completed as part of Coursera's Data Science Specialization Capstone Course, in collaboration with SwiftKey.
We constructed a predictive text model using a Shiny application.
-On the left hand side, type in any sentence you want.
-Click on the Predict button and your input will be filtered, before the next predicted word is generated.
-Some sentences can produce multiple predictions, so the predicted words and their respective likelihoods will be displayed in a table.
-This application required a dataset containing tweets, blogs and news articles.
-Next, the data is cleaned out to remove other characters, punctuation and reduced to lower case.
-Word combinations(known as N-Grams) are created from the dataset, thereby calculating the most likely next word from the user input.
-You can find the application itself on https://vkat722.shinyapps.io/Capstone/
-Any questions or concerns, email me at vkatz722@gmail.com