In my recent project, I’ve delved into the world of natural language processing, using Python along with key libraries like Gensim, Flair, and pyLDAVis. The core of this project involves employing Latent Dirichlet Allocation (LDA) and Sentiment Analysis to dissect the content of books. My goal? To reveal the hidden topics and sentiments concealed within literary works.

For this analysis, I turned to readily available books from the Gutenberg Project, including classics like “Crime and Punishment,” “Alice in Wonderland,” “A Christmas Carol,” and “Metamorphosis.” The result of my analysis is a collection of compelling visualizations, such as word clouds highlighting the most frequently used terms, treemaps showcasing topic structures, and topic sentiment boxplots offering insights into emotional nuances chapter by chapter. What’s even more exciting is that you can use this tool with your own books or online texts, whether you’re an avid reader or a data enthusiast. So, grab a book of your choice and embark on a journey into the world of text analysis!

It’s simple to use and I provided a notebook on how to use it! We have a concept called Bookshelf that takes care of all Books! Then we can simply analyse all, one or a few of these books to extract their sentiment and topics! A lot of visualization are implemeneted there and I hope it will be easy to use :) Find the project in my GitHub: https://github.com/hamzeiehsan/lda_sentiment_books

Have fun coding!

Ehsan