Social media comments and news on Internet regarding any company can impact the flow of stock prices. Forecasting the behavior of stock market is an important obsession for many professionals. Investment banks, evade funds, and insurance companies spend vital time and effort in predicting changes in the stocks. This interest in stock markets has for the last few decades driven the development of better tools for analyzing the mood of general public information. Stock Twits is a micro-blogging platform where a user can post or read messages of up-to 140 characters. Registered user can read or post messages while the unregistered users are only able to read messages. It is mainly used by investors, traders and entrepreneurs who help them to share …show more content…
It contains posts which may be considered as important data about every theme. Through Stock Twits alone, more than 400 Thousand messages are posted for every day. It has at-most 140 characters, that is more than 56 million characters produced every day. Despite the fact that every message may not appear to be greatly significant, it has been used to collect a large amount of message that can provide profitable knowledge about open state of mind and assessment on certain fields. In this work, we use Naive Bayes classification technique of machine learning that are generally use to classify the sentiment out of any sentence. We also intend to find the degree to which messages are associated to stock costs on a day based scale and monthly based scale, and also inquire about which singular words from messages are connected with changes in stock costs. Generally, stock value connections include numerous more variables, however we will simply take a look at the connection between messages and variations on day based scale. The overall aim is to analyze the StockTwits's messages Sentiment posted by the users regarding Stock Market and analyse the flow of stock market with respect to social media