Next Word Predictor Application

• As per https://www.statista.com/statistics/470018/mobile-phone-user-penetration-worldwide/, approx. 66% of the world population today uses a mobile phone.
• Objective of the application is to make it easier for people to type on their mobile devices
• This application predicts the next word given a user entered phrase, by using predictive text modelling techniques

Precursors to building the prediction Model

1. Data acquisition and cleaning
   • For comutational efficiency, here we have utilized only 1% of the english language corpora data
2. We create ngrams (unigrams, bigrams, trigrams and tetragrams) from the processed data

Case1: if user enters only 1 word

• Check if the entered word appears in the training data
  • If the word doesn't exist, suggest top 3 most frequently occuring words, from the Unigram table
  • If the word does exist, suggest top 3 most frequently occuring next words from Bigram table.

Case2: if user enters 2 words

• Check if the entered words appear in the training data (Unigram table)

  • If the second / last word doesnt exist in Unigram table, we suggest the top 3 most frequently occuring words from the Unigram table.
  • If the first word doesnt exist in the training data but the second does, we proceed as if the user has entered only 1 word (the second one), and predict next word as described in case 1.

• If both words exist in the training data, we check if they ever appear together in the entered order, i.e. we check if the bigram formed by these words exists.

  • If the bigram does exist, we look for the most frequently occuring next word from the Trigram table
  • If the bigram doesn't exist, we proceed as if the user has entered only 1 word (the second one), and predict the next word as described in case 1.

case 3: if user enters 3 words

• We extrapolate the process mentioned above to predict the 4th word

case 4: if user enters more than 3 words

• We predict next word considering only the last 3 input words