Text emotion analysis of BGRU model based on the fusion of emoticons

  • Yong Li
  • , Xiao Jun Yang
  • , Min Zuo*
  • , Rui Jun Liu
  • , Qing Yu Jin
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Micro-blog is a platform for users to get information and convey their own ideas. In recent years, the emotional analysis of micro-blog has gradually become a hot topic. The publication of micro blog not only includes text, but also emoticons are a part that cannot be ignored. Traditional research methods ignore the importance of emoticons to the emotional polarity of text when preprocessing the micro blog. This paper proposes a research method of text emotion analysis based on the fusion of emoticons. By micro-blog to crawl the data preprocessing, selected text in the emoticons, using emotional dictionary gives corresponding weights and calculate the score, then transform text into the corresponding word vector sequence, using Bidirectional Gated Recurrent Unit network context information text emotion tendency, finally selects the Conditional Random Field polarity judgment of text. The experimental results show that the accuracy of the proposed method is up to 89%.

Original languageEnglish
Title of host publicationInternational Symposium on Artificial Intelligence and Robotics 2020
EditorsHuimin Lu, Joze Guna, Yujie Li
PublisherSPIE
ISBN (Electronic)9781510639683
DOIs
StatePublished - 2020
Externally publishedYes
EventInternational Symposium on Artificial Intelligence and Robotics 2020 - Kitakyushu, Japan
Duration: 8 Aug 202010 Aug 2020

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume11574
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

ConferenceInternational Symposium on Artificial Intelligence and Robotics 2020
Country/TerritoryJapan
CityKitakyushu
Period8/08/2010/08/20

Keywords

  • BGRU
  • BLSTM
  • CNN
  • CRF
  • Emoticons
  • GRU
  • Machine learning
  • Sentiment analysis

Fingerprint

Dive into the research topics of 'Text emotion analysis of BGRU model based on the fusion of emoticons'. Together they form a unique fingerprint.

Cite this