Document-level sentiment classification in japanese by stem-based segmentation with category and data-source information

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

Abstract

Existing studies focus on text information while ignoring category and data source information, both of which are verified to be important in interpreting sentiments in travel comments in this paper. Furthermore, the unique linguistic characteristics of Japanese cause difficulty in applying the conventional token-based word segmentation methods to Japanese comments directly. In this paper, we propose a method of stem-based segmentation based on Japanese linguistic characteristics and incorporate it with category and data source information into a hierarchical network model for document-level sentiment classification. Empirical results of our proposed model outperform existing models on a real-world dataset.

Original languageEnglish
Title of host publicationProceedings - 14th IEEE International Conference on Semantic Computing, ICSC 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages311-314
Number of pages4
ISBN (Electronic)9781728163321
DOIs
Publication statusPublished - 2020 Feb
Event14th IEEE International Conference on Semantic Computing, ICSC 2020 - San Diego, United States
Duration: 2020 Feb 32020 Feb 5

Publication series

NameProceedings - 14th IEEE International Conference on Semantic Computing, ICSC 2020

Conference

Conference14th IEEE International Conference on Semantic Computing, ICSC 2020
CountryUnited States
CitySan Diego
Period20/2/320/2/5

Keywords

  • Category and data-source information
  • Document-level sentiment classification
  • Japanese
  • Stem-based segmentation

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Document-level sentiment classification in japanese by stem-based segmentation with category and data-source information'. Together they form a unique fingerprint.

  • Cite this

    Bao, S., & Togawa, N. (2020). Document-level sentiment classification in japanese by stem-based segmentation with category and data-source information. In Proceedings - 14th IEEE International Conference on Semantic Computing, ICSC 2020 (pp. 311-314). [9031471] (Proceedings - 14th IEEE International Conference on Semantic Computing, ICSC 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICSC.2020.00062