Presentation 2021-07-15
A Study of Values Extraction in an Open Community for the Purpose of Grasping Social Trends
Keita Suzuki, Shigeru Fujimura, Shigenori Ohashi, Atsushi Nakadaira,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In recent years, the spread of the Internet has created an environment where users can speak out on online platforms, and the number of users is increasing. Therefore, we focus on the concept of values in order to understand social trends. Values are sometimes used together with various concepts that describe a series of people's mental processes, and it is explained that they are based on "desires, demands, and motivations" that direct "attitudes" and lead to "words, deeds, and actions''. In this report, we focus on "attitudes" and aim to understand the trends in the spread of coronaviruses on Twitter. A classifier was constructed by learning linguistic information from Twitter using BERT to classify "attitudes" as "action" or "restricted action" in response to requests for self-restraint by the government and local authorities. As a result of verifying the accuracy of the classifier, we confirmed that it can classify attitudes as well as humans.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) values / classification / Twitter
Paper # LOIS2021-12
Date of Issue 2021-07-08 (LOIS)

Conference Information
Committee LOIS / IPSJ-DC
Conference Date 2021/7/15(1days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Toru Kobayashi(Nagasaki Univ.) / Ryoji Akimoto(Toppan Printing)
Vice Chair Hiroyuki Toda(NTT)
Secretary Hiroyuki Toda(Nagasaki Univ.) / (NTT)
Assistant Kazuki Fukae(Nagasaki Univ.)

Paper Information
Registration To Technical Committee on Life Intelligence and Office Information Systems / Special Interest Group on Document Communication
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Study of Values Extraction in an Open Community for the Purpose of Grasping Social Trends
Sub Title (in English)
Keyword(1) values
Keyword(2) classification
Keyword(3) Twitter
1st Author's Name Keita Suzuki
1st Author's Affiliation NTT Service Evolution Laboratories, NTT Corporation(NTT)
2nd Author's Name Shigeru Fujimura
2nd Author's Affiliation NTT Service Evolution Laboratories, NTT Corporation(NTT)
3rd Author's Name Shigenori Ohashi
3rd Author's Affiliation NTT Service Evolution Laboratories, NTT Corporation(NTT)
4th Author's Name Atsushi Nakadaira
4th Author's Affiliation NTT Service Evolution Laboratories, NTT Corporation(NTT)
Date 2021-07-15
Paper # LOIS2021-12
Volume (vol) vol.121
Number (no) LOIS-111
Page pp.pp.1-5(LOIS),
#Pages 5
Date of Issue 2021-07-08 (LOIS)