Presentation 2022-05-27
[Poster Presentation] Performance Evaluation of Twitter Classification on Pre-Trained Model by Word Embeddings
Haruki Kimura, Incheon Paik,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The Internet is used as social infrastructure to such an extent that modern society would not be possible without it. With the development of the Internet, various data has been accumulated on the Web. What I would like to focus on here are social networking services. Today, we live in an age where everyone can send out information, and the information sent out by individuals on SNS contains a variety of emotions. If we can analyze this information, we can apply it to various things. We will use the data collected from Twitter to analyze emotions. In 2018, a natural language processing model called BERT was released by Google. A previous study compared BERT with earlier methods and showed that BERT effectively analyzes Twitter sentiment. In this study, we use a model that has already been pre-trained and compare the accuracy by changing the batch size and data size. As a result, we were able to get better results than the previous study by reducing the batch size and data size.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) natural language processing / Twitter / sentiment analysis / BERT
Paper # SC2022-15
Date of Issue 2022-05-20 (SC)

Conference Information
Committee SC
Conference Date 2022/5/27(1days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English) AI Service and Digital Transformation, and general topics
Chair Shinji Kikuchi(NIMS)
Vice Chair Yoji Yamato(NTT) / Kosaku Kimura(Fujitsu)
Secretary Yoji Yamato(Kobe Univ.) / Kosaku Kimura(Tokyo Univ. of Tech.)
Assistant Shin Tezuka(Hitachi) / Takao Nakaguchi(KCGI)

Paper Information
Registration To Technical Committee on Service Computing
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) [Poster Presentation] Performance Evaluation of Twitter Classification on Pre-Trained Model by Word Embeddings
Sub Title (in English)
Keyword(1) natural language processing
Keyword(2) Twitter
Keyword(3) sentiment analysis
Keyword(4) BERT
1st Author's Name Haruki Kimura
1st Author's Affiliation University of Aizu(UoA)
2nd Author's Name Incheon Paik
2nd Author's Affiliation University of Aizu(UoA)
Date 2022-05-27
Paper # SC2022-15
Volume (vol) vol.122
Number (no) SC-50
Page pp.pp.88-92(SC),
#Pages 5
Date of Issue 2022-05-20 (SC)