A Moral Judgment System Using an Automatic Created Moral Corpus

Masahiro Yamamoto, Masafumi Hagiwara

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

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.

Original languageEnglish
Title of host publicationProceedings - 2016 Joint 8th International Conference on Soft Computing and Intelligent Systems and 2016 17th International Symposium on Advanced Intelligent Systems, SCIS-ISIS 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages616-621
Number of pages6
ISBN (Electronic)9781467390415
DOIs
Publication statusPublished - 2016 Dec 28
Event8th Joint International Conference on Soft Computing and Intelligent Systems and 17th International Symposium on Advanced Intelligent Systems, SCIS-ISIS 2016 - Sapporo, Hokkaido, Japan
Duration: 2016 Aug 252016 Aug 28

Publication series

NameProceedings - 2016 Joint 8th International Conference on Soft Computing and Intelligent Systems and 2016 17th International Symposium on Advanced Intelligent Systems, SCIS-ISIS 2016

Other

Other8th Joint International Conference on Soft Computing and Intelligent Systems and 17th International Symposium on Advanced Intelligent Systems, SCIS-ISIS 2016
Country/TerritoryJapan
CitySapporo, Hokkaido
Period16/8/2516/8/28

Keywords

  • moral judgment
  • text mining
  • web corpus

ASJC Scopus subject areas

  • Control and Optimization
  • Artificial Intelligence
  • Software
  • Computational Mathematics
  • Modelling and Simulation

Fingerprint

Dive into the research topics of 'A Moral Judgment System Using an Automatic Created Moral Corpus'. Together they form a unique fingerprint.

Cite this