Presentation 2021-07-24
Social Emotional Change Estimation using Twitter
Fujio Toriumi, Michimasa Inaba,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we developed a new emotion estimation model using BERT to extract social emotions from Twitter. The accuracy of the model was evaluated by subject experiments. The proposed model succeeded to estimate emotions with an accuracy of $80~90%$, which is higher than MLAsk, a commonly used emotion estimation method. We also extracted and analyzed emotion toward the COVID-19 vaccine using the proposed model. The results showed that the emotions toward the vaccine changed depending on the period and that positive emotions increased as the number of vaccinations increased.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Social Media / Twitter / Emotion analysis / COVID-19 / Vaccine
Paper # DE2021-11
Date of Issue 2021-07-17 (DE)

Conference Information
Committee DE
Conference Date 2021/7/24(1days)
Place (in Japanese) (See Japanese page)
Place (in English) KAIT IT extension center (Hybrid)
Topics (in Japanese) (See Japanese page)
Topics (in English) Social Computing
Chair Naofumi Yoshida(Komazawa Univ.)
Vice Chair Akiyoshi Matono(AIST) / Yu Suzuki(Gifu Univ.)
Secretary Akiyoshi Matono(Kanagawa Inst. of Tech.) / Yu Suzuki(Osaka Univ.)
Assistant Ken Honda(Komazawa Univ.) / Hiroki Nomiya(Kyoto Inst. of Tech)

Paper Information
Registration To Technical Committee on Data Engineering
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Social Emotional Change Estimation using Twitter
Sub Title (in English)
Keyword(1) Social Media
Keyword(2) Twitter
Keyword(3) Emotion analysis
Keyword(4) COVID-19
Keyword(5) Vaccine
1st Author's Name Fujio Toriumi
1st Author's Affiliation The University of Tokyo(UT)
2nd Author's Name Michimasa Inaba
2nd Author's Affiliation The University of Electro-Communications(UEC)
Date 2021-07-24
Paper # DE2021-11
Volume (vol) vol.121
Number (no) DE-125
Page pp.pp.58-62(DE),
#Pages 5
Date of Issue 2021-07-17 (DE)