Emotion Estimation Adapted to Gender of User Based on Deep Neural Networks

機関リポジトリ

抄録

In this study, we focus on Twitter as a representative SNS and target emotion estimation from tweets posted on Twitter by male and female users. Specifically, we construct gender-based emotion estimation models assuming that there are different word usage tendencies between genders. By analyzing gender-specific differences in the use of emotion-related slang and emoji, we propose a method to improve emotion estimation based on neural networks using a different distributed representation model for each gender. Our evaluation experiments show that training with Deep Convolutional Neural Networks using word's distributed representation as the feature produced higher estimation accuracy than training with Feed Forward Neural Networks.

収録刊行物

関連プロジェクト

もっと見る

キーワード

詳細情報 詳細情報について

  • CRID
    1050564288205659776
  • NII論文ID
    120006627855
  • ISSN
    18833918
  • Web Site
    http://repo.lib.tokushima-u.ac.jp/113250
  • 本文言語コード
    en
  • 資料種別
    journal article
  • データソース種別
    • IRDB
    • CiNii Articles
    • KAKEN

問題の指摘

ページトップへ