A Moral Judgment System Using an Automatic Created Moral Corpus

In this paper, we propose a moral judgment system using an automatic created moral corpus. The moral corpus enables that the correct judgment to the case that the existing methods cannot judge correctly. Here, the moral corpus means the set of sentences that are labeled "positive" or "negative" from the point of view of morality. In the proposed system, the moral corpus is created automatically from a large web corpus using lexical patterns and evaluation expressions. The moral corpus which contains about 300,000 instances was created. After that, a supervised learning is performed using the moral corpus. In the experiments, we compared the proposed system with judgments by human. The results of our experiments indicate that our method significantly outperforms the existing method which is based on the co-occurrence frequency.