Next Word Predictor

Author: Vijay Mishra

This presentation will pitch an application for predicting the next word.

The main goal of this capstone project is to build a shiny application that is able to predict the next word.

This exercise was divided into seven sub tasks like data cleansing, Exploratory Data Analysis, the creation of a predictive model.

All text data that is used to create a frequency dictionary and thus to predict the next words comes from a corpus called HC Corpora.

This data sample was then tokenized into so-called n-grams.

In the fields of computational linguistics and probability, an n-gram is a contiguous sequence of n items from a given sequence of text or speech. (Source Link)

Those aggregated bi-,tri- and quadgram term frequency matrices have been transferred into frequency dictionaries.

The resulting data.frames are used to predict the next word in connection with the text input by a user of the described application and the frequencies of the underlying n-grams table.

• The next word prediction app is hosted on shinyapps.io: https://bkvijay.shinyapps.io/ShinyApp/

• About Author LinkedIn Page: https://www.linkedin.com/in/vijaymishra17/