I. Introduction
The popularity of social media website such as Twitter, Face- book has increased exponentially in recent past. These social media websites have become a direct platform for the people to express their feelings, opinions about a particular topic, event or product. The proper analysis of such microblog data can help an individual or society in a better way. Therefore, the process of identification of sentiments has become paramount in the field of data mining. It helps in determining whether a piece of text expresses a positive, negative or neutral sentiment. It can also be termed as Opinion Mining as the process tells the changes in public opinion about an event. Significant events like terrorist attacks, sports events, natural disasters are widely discussed topics over social media. Twitter is one of those microbloging sites and widely used platform for emotions manifestation & flooding the views to the intended community. This assistance of twitter has turned as the habit of users. Cricket is like religion for Indians and so it can not stay away untouched from tweeting trends. Throughout the past, it is observed that Indians are very emotionally attached with cricket. This gives us an idea to capture these flowing emotions of Indian cricket lovers. From the previous studies (Bollen, Mao, and Zeng 2011), it was observed that emotions drive the trading. Therefore, it motivates us to study one to one correspondence between the social emotions and trading behavior. Cricket fans follow all the liking and disliking of their role models (Sachin Tendulkar). In this era of high competition, companies strive to connect with a huge population of the country through their superstars as a bridge. Therefore, the performance of the player who is the brand ambassador of some company becomes very crucial for advertising their brand in the market. In this study, we have categorized the sentiment of fans for their team & for their favorite player among positive and negative sentiments. In the present work, we have extracted pre-match & post-match emotions. After that try to established the relationship between the fans sentiments and players performance.