Mixed bilingual social media analytics: case study: Live Twitter data

The rise of social media has brought about a new realm for people all over the globe to interact and share information and opinions. Twitter, Facebook, Blogs, Google+, etc. have become the most sought after platforms for people to share their opinions, feelings and feedback about the latest trends and products. Unlike formal documentation, people are free to express themselves in multiple languages, by mixing two languages and most notably in India, in `Hinglish', a culmination of English and Hindi. The proposed system classifies Hinglish Tweets from Twitter platform, according to the sentiment expressed by the users, for example, `I won lottery! Ab mein amir hoon!' will be considered as a positive tweet. The Hindi dictionaries built for the system have been equipped with spelling ambiguities.