Emotion prediction and cause analysis considering spatio-temporal distribution

Saki Kitaoka, Takashi Hasuike

研究成果: Article

抄録

This paper proposes an analytical model that clarifies the relationship between specific place and human emotions as well as the cause of the emotions using tweet data with location information. In addition, Twitter data with location information are analyzed to show the effectiveness of our proposed model. First, geotags are provided to collect Twitter data and increase the number of data for analysis. Second, training data with emotion labels based on the emotion expression dictionary are created and used, and supervised learning is done using fastText to obtain the emotion estimates. Finally, by using the result, topic extraction is performed to estimate the causes of the emotions. As a result, the transition of emotion in time and space as well as its cause is obtained.

元の言語English
ページ(範囲)512-518
ページ数7
ジャーナルJournal of Advanced Computational Intelligence and Intelligent Informatics
23
発行部数3
DOI
出版物ステータスPublished - 2019 5 1

Fingerprint

Supervised learning
Glossaries
Labels
Analytical models

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

これを引用

@article{98fdd1ad241045df88208f032c775a74,
title = "Emotion prediction and cause analysis considering spatio-temporal distribution",
abstract = "This paper proposes an analytical model that clarifies the relationship between specific place and human emotions as well as the cause of the emotions using tweet data with location information. In addition, Twitter data with location information are analyzed to show the effectiveness of our proposed model. First, geotags are provided to collect Twitter data and increase the number of data for analysis. Second, training data with emotion labels based on the emotion expression dictionary are created and used, and supervised learning is done using fastText to obtain the emotion estimates. Finally, by using the result, topic extraction is performed to estimate the causes of the emotions. As a result, the transition of emotion in time and space as well as its cause is obtained.",
keywords = "Biterm topic model, Emotion estimation, Spatio-temporal distribution, Twitter-LDA",
author = "Saki Kitaoka and Takashi Hasuike",
year = "2019",
month = "5",
day = "1",
doi = "10.20965/jaciii.2019.p0512",
language = "English",
volume = "23",
pages = "512--518",
journal = "Journal of Advanced Computational Intelligence and Intelligent Informatics",
issn = "1343-0130",
publisher = "Fuji Technology Press",
number = "3",

}

TY - JOUR

T1 - Emotion prediction and cause analysis considering spatio-temporal distribution

AU - Kitaoka, Saki

AU - Hasuike, Takashi

PY - 2019/5/1

Y1 - 2019/5/1

N2 - This paper proposes an analytical model that clarifies the relationship between specific place and human emotions as well as the cause of the emotions using tweet data with location information. In addition, Twitter data with location information are analyzed to show the effectiveness of our proposed model. First, geotags are provided to collect Twitter data and increase the number of data for analysis. Second, training data with emotion labels based on the emotion expression dictionary are created and used, and supervised learning is done using fastText to obtain the emotion estimates. Finally, by using the result, topic extraction is performed to estimate the causes of the emotions. As a result, the transition of emotion in time and space as well as its cause is obtained.

AB - This paper proposes an analytical model that clarifies the relationship between specific place and human emotions as well as the cause of the emotions using tweet data with location information. In addition, Twitter data with location information are analyzed to show the effectiveness of our proposed model. First, geotags are provided to collect Twitter data and increase the number of data for analysis. Second, training data with emotion labels based on the emotion expression dictionary are created and used, and supervised learning is done using fastText to obtain the emotion estimates. Finally, by using the result, topic extraction is performed to estimate the causes of the emotions. As a result, the transition of emotion in time and space as well as its cause is obtained.

KW - Biterm topic model

KW - Emotion estimation

KW - Spatio-temporal distribution

KW - Twitter-LDA

UR - http://www.scopus.com/inward/record.url?scp=85066237447&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066237447&partnerID=8YFLogxK

U2 - 10.20965/jaciii.2019.p0512

DO - 10.20965/jaciii.2019.p0512

M3 - Article

AN - SCOPUS:85066237447

VL - 23

SP - 512

EP - 518

JO - Journal of Advanced Computational Intelligence and Intelligent Informatics

JF - Journal of Advanced Computational Intelligence and Intelligent Informatics

SN - 1343-0130

IS - 3

ER -