Japanese emotion corpus analysis and its use for automatic emotion word identification

Abstract

In this paper, the creation of a Japanese emotion corpus and its use in automatic emotion word identification are examined. The corpus was created by manually tagging words in just under 1,200 dialog sentences with emotion. Using the tagged corpus, statistical analysis was performed to determine the characteristics of emotional expression in Japanese dialog. This type of analysis should prove beneficial for understanding how emotion is expressed and how to identify, classify, etc. emotion in Japanese. To test this theory an automatic emotion word identification system was built using machine learning based classifiers with features taken from the statistical analysis. In total, four different classifiers were trained and compared to a baseline dictionary approach. It was found that classifier based identification was able to significantly increase recall.