The project aims at understanding the impact of titles and other features of a existing and published books to obtain insights and areas of improvements for the future releases.
It is developed using Python programming language and packages including pandas, numpy, matplotlib, seaborn, nltk and scikit-learn.
The data for this project is a real-time data gathered from amazon.in using the web-scrapper tool 'ParseHub'. It involves exploratory data analysis of the released books and how their respective features have affected their success amongst readers in the market. The project also classifies books into different categories based on their ratings, price, and years since they've been released.
Each book's title is analysed to extract insights about the popular and trending topics and genres among readers. The reviews of these books are then analysed to identify the sentiment being shown in them.
