User generated content on Twitter (produced at an enormous rate of 340 million tweets per day) provides a rich source for gleaning people's emotions, which is necessary for deeper understanding of people's behaviors and actions. Extant studies on emotion identification lack comprehensive coverage of "emotional situations" because they use relatively small training datasets. To overcome this bottleneck, we have automatically created a large emotion-labeled dataset (of about 2.5 million tweets) by harnessing emotion-related hash tags available in the tweets. We have applied two different machine learning algorithms for emotion identification, to study the effectiveness of various feature combinations as well as the effect of the size of the training data on the emotion identification task. Our experiments demonstrate that a combination of unigrams, big rams, sentiment/emotion-bearing words, and parts-of-speech information is most effective for gleaning emotions. The highest accuracy (65.57%) is achieved with a training data containing about 2 million tweets.
Available at: http://works.bepress.com/tk_prasad/66/