Prediction App Presentation

Andrés Felipe Palacios Clavijo
07/February/2021

As part of the Coursera Data Science Specialization, I present the final product of the Capstone Project course.

The prediction algorithm can be seen in a shiny app in which you can predict the next word based on the sentence you just wrote.

This next word prediction algorithm uses the principles of “tidy data” applied to text mining in R.

First, raw text files are used for model training.

After it, a list of n-grams where n is 2, 3 and 4, is generated and saved summarizing the text data from the raw text files.

Saved n-grams provides the best last 3, 2, or 1 words to predict the next word to the sentence

The next word is presented as the prediction from the words user writes.

On this link you can test the prediction algorithm with you own word or list of words