The mission of the project is to clean a raw database and present the data on on what people read or write in the online news, social media and blogs within one sample year in order to pass a JHU course project.

Internet is an important source of data nowadays - and effective statistical and IT ways to proceed its big data are of a high interest.

This project uses the .txt format raw (unclenaed) data in the original languages as they are.

The data dorcessing methods documentation presentation may be found here: https://web.stanford.edu/~jurafsky/NLPCourseraSlides.html.

The data itself may be found here.

The project is made in R which is a statistical programming language free software. The code samples are represented in this text.

• Single Function For R Environment Complex Prediction
• Function For Shiny
• Midterm Report
• Final Project Presentation

• Special Function Is Designed For This Issue: getWords()
• It Will Both Suggest The Next Words
• And Will Plot Wordcloud Representing Words + Probabilities

• The Internal R Function Needs Around 2-3 Seconds To Predict The Next Word(s)
• The Shiny Application Needs Less Than 1 Second To Produce 1 Each Next Word

• Shiny Server Time Limit Per User
• Processing Unusual Symbols From Non-English Languages
• Stopwords: If Use Or Not For Training The Model

Thank You Very Much For Your Attention! I Hope You Will Like My Project.