Sentimental analysis is a very popular area in computational linguistics. 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.
The analysis should be automatized since a timing of determining public moods is crucial for its value. There are numerous tools for understanding public opinions such as a survey, but most of them needs enormous efforts and lengthy time. The solution is to use computational models for analyzing public media, such as blogs and twitter. I will use machine learning methodologies to build a model to have theoretical supports since designing such a complex model is beyond of manual modeling.
current active research topic