With the advent of technology, Sentiment polarity detection has recently piqued the interest of NLP researchers. Sentiment analysis determines the profound meaning of an article. Due to COVID-19 pandemic, online shopping is the safest way of shopping. Moreover, there are product quality and service issues. Our target is to analyze the book reviews which provide positive and negative reviews in Bangla language. For this, a total of 5500 user generated Bengali reviews are collected from various book review pages of social media. In order to get the best possible result, sentiment analysis is used. Thereafter, five different algorithms are applied to predict with almost high accuracy. Among them, the Random Forest provides us the maximum accuracy which is 98.39%.