Text Prediction App

Wagner Pinheiro
March, 2017

JHU Data Science Specialization Capstone Project

The Project

This app uses a predictive model using Markov Chains to suggest the next user word. This model was defined from the analysis of n-grams in a collection of texts extracted from blogs, twitter and news.

The texts dataset used can be accessed here.

Some Statistics

Above you can see a word cloud of twitter analysed text.

For a more detailed statistics see this report.

word cloud

The App

Test the Shiny App Predict Text: https://wagnerpinheiro.shinyapps.io/predict_text/

Screenshot:

screenshot

Resources and References

References

  1. https://en.wikipedia.org/wiki/Natural_language_processing
  2. http://cran.r-project.org/web/views/NaturalLanguageProcessing.html
  3. https://www.coursera.org/course/nlp
  4. https://cran.r-project.org/web/packages/quanteda/vignettes/quickstart.html
  5. https://cran.r-project.org/web/packages/tidytext/vignettes/tidying_casting.html