• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

A Study on Affect Estimation Methods with Machine Learning from Training Data of Japanese Text

Research Project

Project/Area Number 24650061
Research Category

Grant-in-Aid for Challenging Exploratory Research

Allocation TypeMulti-year Fund
Research Field Intelligent informatics
Research InstitutionHokkaido University

Principal Investigator

Oyama Satoshi  北海道大学, 情報科学研究科, 准教授 (30346100)

Project Period (FY) 2012-04-01 – 2016-03-31
Project Status Completed (Fiscal Year 2015)
Budget Amount *help
¥3,900,000 (Direct Cost: ¥3,000,000、Indirect Cost: ¥900,000)
Fiscal Year 2014: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2013: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2012: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Keywords機械学習 / 感性情報学 / 人工知能 / クラウドソーシング
Outline of Final Research Achievements

Estimating affects from text is a key technology for many applications such as text-to-speech synthesis and affective education. In this study, we specifically dealt with the problem of estimating affects of characters’ utterances in narrative text. We enabled accurate affect estimation from crowdsourced labels by considering dependency between affect labels, affective tendency of the story and characters, and contextual cues in the story. We also developed algorithms for enabling interoperability between different affect models.

Report

(5 results)
  • 2015 Annual Research Report   Final Research Report ( PDF )
  • 2014 Research-status Report
  • 2013 Research-status Report
  • 2012 Research-status Report
  • Research Products

    (15 results)

All 2016 2015 2014 2013 Other

All Journal Article (5 results) (of which Peer Reviewed: 5 results,  Acknowledgement Compliant: 2 results) Presentation (9 results) (of which Int'l Joint Research: 2 results) Book (1 results)

  • [Journal Article] Separate or Joint? Estimation of Multiple Labels from Crowdsourced Annotations2014

    • Author(s)
      Lei Duan, Satoshi Oyama, Haruhiko Sato, Masahito Kurihara
    • Journal Title

      Expert Systems With Applications

      Volume: 41(13) Issue: 13 Pages: 5723-5732

    • DOI

      10.1016/j.eswa.2014.03.048

    • NAID

      120005517715

    • Related Report
      2014 Research-status Report
    • Peer Reviewed / Acknowledgement Compliant
  • [Journal Article] A Survey on Large Scale Corpora and Emotion Corpora2014

    • Author(s)
      Michal Ptaszynski, Rafal Rzepka, Satoshi Oyama, Masahito Kurihara, Kenji Araki
    • Journal Title

      コンピュータソフトウェア

      Volume: 31(2) Pages: 151-167

    • NAID

      130004705278

    • Related Report
      2014 Research-status Report
    • Peer Reviewed / Acknowledgement Compliant
  • [Journal Article] Separate or Joint? Estimation of Multiple Labels from Crowdsourced Annotations2014

    • Author(s)
      Lei Duan, Satoshi Oyama, Haruhiko Sato, and Masahito Kurihara
    • Journal Title

      Expert Systems with Applications

      Volume: 未定

    • NAID

      120005517715

    • Related Report
      2013 Research-status Report
    • Peer Reviewed
  • [Journal Article] Survey on Large Scale Corpora and Emotion Corpora2014

    • Author(s)
      Michal Ptaszynski, Rafal Rzepka, Satoshi Oyama, Masahito Kurihara, and Kenji Araki
    • Journal Title

      コンピュータソフトウェア

      Volume: 未定

    • NAID

      130004705278

    • Related Report
      2013 Research-status Report
    • Peer Reviewed
  • [Journal Article] Affect Analysis in Context of Characters of Narratives2013

    • Author(s)
      Michal Ptaszynski, Hiroaki Dokoshi, Satoshi Oyama, Rafal Rzepka, Masahito Kurihara, Kenji Araki and Yoshio Momouchi
    • Journal Title

      Expert Systems With Applications

      Volume: 40(1) Issue: 1 Pages: 168-176

    • DOI

      10.1016/j.eswa.2012.07.025

    • Related Report
      2012 Research-status Report
    • Peer Reviewed
  • [Presentation] Crowdsourced Semantic Matching of Multi-Label Annotations2015

    • Author(s)
      Lei Duan, Satoshi Oyama, Masahito Kurihara, Haruhiko Sato
    • Organizer
      24th International Joint Conference on Artificial Intelligence (IJCAI 2015)
    • Place of Presentation
      Buenos Aires, Argentina
    • Year and Date
      2015-07-25
    • Related Report
      2015 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Multi-Emotion Estimation in Narratives from Crowdsourced Annotations2015

    • Author(s)
      Lei Duan, Satoshi Oyama, Haruhiko Sato, Masahito Kurihara
    • Organizer
      ACM/IEEE Joint Conference on Digital Libraries (JCDL 2015)
    • Place of Presentation
      University of Tennessee Conference Center (Knoxville, Tennessee, USA)
    • Year and Date
      2015-06-21 – 2015-06-25
    • Related Report
      2014 Research-status Report
  • [Presentation] Multi-Emotion Estimation in Narratives from Crowdsourced Annotations2015

    • Author(s)
      Lei Duan, Satoshi Oyama, Haruhiko Sato, Masahito Kurihara
    • Organizer
      15th ACM/IEEE-CS Joint Conference on Digital Libraries (JCDL 2015)
    • Place of Presentation
      Knoxville, TN, USA
    • Year and Date
      2015-06-21
    • Related Report
      2015 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Establishing Relationships between Emotion Taxonomies Using the Vector Space Model2015

    • Author(s)
      Lei Duan, Satoshi Oyama, Masahito Kurihara, Haruhiko Sato
    • Organizer
      2015 IAENG International Conference on Artificial Intelligence and Applications (ICAIA)
    • Place of Presentation
      The Royal Garden (Hong Kong, China)
    • Year and Date
      2015-03-18 – 2015-03-20
    • Related Report
      2014 Research-status Report
  • [Presentation] Leveraging Crowdsourcing to Make Models in Multi-label Domains Interoperable2014

    • Author(s)
      Lei Duan, Satoshi Oyama, Haruhiko Sato, Masahito Kurihara
    • Organizer
      情報処理北海道シンポジウム2014
    • Place of Presentation
      北海道函館市 公立はこだて未来大学
    • Year and Date
      2014-10-04
    • Related Report
      2014 Research-status Report
  • [Presentation] Multi-affect Estimation Considering Consistencies among Crowdsourced Annotations2014

    • Author(s)
      Lei Duan, Satoshi Oyama, Haruhiko Sato, Masahito Kurihara
    • Organizer
      第28回人工知能学会全国大会
    • Place of Presentation
      愛媛県松山市 ひめぎんホール(愛媛県県民文化会館)他
    • Year and Date
      2014-05-12 – 2014-05-15
    • Related Report
      2014 Research-status Report
  • [Presentation] Multi-affect Estimation Considering Consistency among Crowdsourced Annotations2014

    • Author(s)
      Lei Duan, Satoshi Oyama, Haruhiko Sato, and Masahito Kurihara
    • Organizer
      第28回人工知能学会全国大会
    • Place of Presentation
      愛媛県松山市 ひめぎんホール(愛媛県県民文化会館)他
    • Related Report
      2013 Research-status Report
  • [Presentation] 物語文における心情推定の研究2013

    • Author(s)
      段 磊, 小山 聡, 栗原 正仁, 佐藤 晴彦
    • Organizer
      情報処理学会第75回全国大会
    • Place of Presentation
      東北大学川内キャンパス(仙台市)
    • Related Report
      2012 Research-status Report
  • [Presentation] Joint Estimation of Multiple Affects from Crowdsourced Annotations

    • Author(s)
      Lei Duan, Satoshi Oyama, Haruhiko Sato, and Masahito Kurihara
    • Organizer
      情報処理北海道シンポジウム2013
    • Place of Presentation
      北海道室蘭市 室蘭工業大学
    • Related Report
      2013 Research-status Report
  • [Book] ヒューマンコンピュテーションとクラウドソーシング2016

    • Author(s)
      鹿島 久嗣, 小山 聡, 馬場 雪乃
    • Total Pages
      117
    • Publisher
      講談社
    • Related Report
      2015 Annual Research Report

URL: 

Published: 2013-05-31   Modified: 2019-07-29  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi