Scientific research based
According to Asur and Huberman social media content can be used to predict real-world outcomes. In particular, they use the chatter from Twitter to forecast box-office revenues for movies. A model built from the rate at which tweets are created about particular topics can outperform market-based predictors.
Sentiments extracted from Twitter can be utilized to further improve the forecasting power of social media.
Behavioral economics tells us that emotions can profoundly affect individual behavior and decision making. Bollen et al.'s research results indicate that the accuracy of Dow Jones Industrial Average index predictions can be significantly improved by the inclusion of specific public mood dimensions (mood states), especially the calmness of an audience.