The goal of this project is to utilize Natural Language Processing methods to analyze the The Hobbit, by J.R.R. Tolkein.
Current aims include:
- Identify characteristics of the writing (# of unique words, # of most frequent words, average sentence length, etc).
- Characterize the interactions between the main character and key supporting characters.
- Track sentiment analysis of characters over the length of the novel.
- Form a conclusion based on quantitative evidence.
Because I am a novice programmer, I plan to use the basic Natural Language Tool Kit (NLTK) packages for python in this project. In the future, I hope to expand my skillset to other models: TextBlob, spaCy, Vader sentiment. I also plan to use pandas & matplotlib to organize and visualize data.