This project builds a next-word prediction model using natural language processing techniques.

Goals:

• Uses n-gram modeling (trigrams)
• Predicts the next word based on previous two words
• Built and deployed as a Shiny web application

The model is trained on three datasets (Blogs, News, and Twitter) and processed into trigrams. A sample of the data was used to improve performance and reduce computation time

Steps:

• Convert text to lowercase
• Remove punctuation
• Tokenize into words
• Build trigram frequency table

Example:

• Input: “I love data”
• Model learns: “I love → data”

The prediction function: - Cleans input text (lowercase, remove punctuation) - Splits input into words - Uses pattern matching to find matching trigrams

matches <- trigram_df[grepl(paste0("^", last_two), trigram_df$text), ]
predicted <- most_freq_word(matches)

• Returns the most frequent next word

The Shiny app allows users to:

1. Enter a phrase
2. Click “Predict”
3. View the next word instantly

The application includes:

• Simple and clean user interface
• Real-time prediction
• Input validation (requires at least two words)
• Fast response using precomputed n-grams

Key achievements:

• Built a functional NLP prediction model
• Demonstrated how n-grams predict language patterns
• Delivered an interactive web application