#Advanced Big Data Analytics

Building basic NLTK modules

  • Basic Chunking implemented
  • Chunking could be used to figure out how many other proper nouns are spoken about in Donald Trumps supports.
  • Chinking may also be a good resource, but i think i will stick to using Chunks
  • Named Entity recongnition completed. Has a very valid use case. Will still have to figure out its best use-case application
  • Wordnet is a powerful tool to find synonyms and antonymns. Possible use case could be to translate words which are in a foreign language. I think that the use case viability is limited by the fact that it cant recognise the language on its own. (Google translate api could be a better fit)
  • The file better_text_classification.py has code to save pickle commented out
  • NLTK modules now has the completed Sentiment Analysis Module
  • The module is in the file senti_final.py
  • Add text and run the file : run_sentiment_analysis.py to check the results of sentiment analysis
  • The file final_chunk.py contains the working code for chunking