Abstract
On a worldwide level, every second around 6000 tweets are sent, which counts to around 200 billion tweets in a year. People share their ideas and views publicly on Twitter, thus it serves as a good platform for analyzing public trends and behaviour towards any person, product or news. Customers frequently utilize social media platforms to share their thoughts and experiences regarding goods and services. Businesses can find areas for improvement and better understand the attitudes of their customers towards their goods and services by using sentiment analysis. In order to perform sentiment analysis on twitter, text classification using Natural Language Processing(NLP) has been proved to be very helpful. Using NLP word tokenizer, we can divide the sentences into different sets of words, thereafter we remove the stop words. Manually tokenizing long tweets and categorizing them into separate groups is challenging. The primary goal of this model is to analyze the tweets related to a given keyword entered by the user, classify the tweets as positive, negative or neutral using (VADER sentiment analysis or alternately). TextBlob library, which will help consumers as well as manufacturers to understand people's overall opinion regarding the product. This study makes an attempt to suggest a text sentiment analysis on twitter data using the NLTK and TextBlob libraries.