The “Input predictor” is a Shiny app that predicts the most probable word next to the input phase.

Input predictor link: “https://liujun0402.shinyapps.io/Input_prediction/”

Github link: “https://github.com/lj231024/Input-predictor”

1. Enter a text phrase into the “Enter text phrase without last word:” block.
   
2. Choose a mode.
   
3. Click “Submit” button
4. Wait several second for processing
5. check the word in “Predicted next word:” block.
6. The context will shown in “Predicted phrase:”block.

1. Fast mode predicts the most probable word using 1% phrase dataset that combined Twitter, Blog and News.

2. Compete mode predicts the most probable word using 100% phrase dataset that combined Twitter, Blog and News.

Notice: The Complete mode is not available for the online shiny app because of the data size limitation.

The phrase terms combined Twitter, Blog, and News were the first to pick through n-gram algorithm. Here, we used 6-gram to catch a short phrase but contains enough information.

Then the last three words in the input will be used to match with the 6-gram phrases.

The 6-gram phrases contained interesting information then picked through 2-gram algorithm.

And then, the most frequent phrase with the last input word will be the predicted word.

If there is no matched word, the most frequent word “the” will be used as predicted word.

The goal of this exercise is to create a product to highlight the prediction algorithm that you have built and to provide an interface that can be accessed by others. For this project you must submit:

A Shiny app that takes as input a phrase (multiple words) in a text box input and outputs a prediction of the next word.

A slide deck consisting of no more than 5 slides created with R Studio Presenter (https://support.rstudio.com/hc/en-us/articles/200486468-Authoring-R-Presentations) pitching your algorithm and app as if you were presenting to your boss or an investor.

Thank you for your time!