As there are huge needs of understanding public opinions, sentimental analysis is one of actively researched area. However, determining only positive or negative sentiment has obvious limitation. Happy is clearly a positive sentiment, but how can we determine curious whether it is positive or negative? Curious is one of fundamental human affect. Detecting such moods that cannot be determined by bipolar sentiment could be invaluable information to comprehend the public. For example, we can discover which public news is most people is interested in by detecting a mood of interested.
We consider higher dimensional extensions of the sentiment concept, which represent a richer set of human emotions. Our approach goes beyond previous work in that our model contains a continuous manifold rather than a finite set of human emotions.
Seungyeon Kim, Joonseok Lee, Guy Lebanon and Haesun Park. Estimating Temporal Dynamics of Human Emotions. Proceedings of the 29th AAAI Conference on Artificial Intelligence (AAAI). 2015. pdf
Seungyeon Kim, Fuxin Li, Guy Lebanon, and Irfan Essa. Beyond Sentiment: The Manifold of Human Emotions. Proceedings of the 16th International Conference on Artificial Intelligence and Statistics (AISTATS), 2013. pdf