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

研究成果: Conference contribution

1 被引用数 (Scopus)

抄録

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.

本文言語English
ホスト出版物のタイトルProceedings - 14th IEEE International Conference on Semantic Computing, ICSC 2020
出版社Institute of Electrical and Electronics Engineers Inc.
ページ311-314
ページ数4
ISBN(電子版)9781728163321
DOI
出版ステータスPublished - 2020 2月
イベント14th IEEE International Conference on Semantic Computing, ICSC 2020 - San Diego, United States
継続期間: 2020 2月 32020 2月 5

出版物シリーズ

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

Conference

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

ASJC Scopus subject areas

  • 人工知能
  • コンピュータ サイエンスの応用
  • コンピュータ ビジョンおよびパターン認識

フィンガープリント

「Document-level sentiment classification in japanese by stem-based segmentation with category and data-source information」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル