Proceedings of the 2022 International Conference on Computer Science, Information Engineering and Digital Economy (CSIEDE 2022)

Sentiment Analysis of Microblog During the COVID-19 Pandemic Based on NEZHA Model

Authors
Fan Yang1, *
1Huazhong University of Science and Technology, Wuhan, China
*Corresponding author. Email: 18186270199@163.com
Corresponding Author
Fan Yang
Available Online 30 December 2022.
DOI
10.2991/978-94-6463-108-1_42How to use a DOI?
Keywords
Deep learning; Text sentiment analysis; NEZHA; Whole word masking; Functional positional encoding
Abstract

Microblog sentiment analysis aims at mining the opinions and views of Internet users on specific events, which is an important content of network public opinion monitoring. The current microblog sentiment analysis generally selects the BERT model proposed by Google, which has no targeted improvement for Chinese text. While there are many improved models based on Bert and the NEZHA (Neural Contextualized Representation for Chinese Language Understanding) model is one of them which is developed by Noah's Ark Lab. The whole word masking technique and functional position encoding mechanism are introduced in the model which can reach the advanced level in a series of Chinese natural language understanding tasks. At present, there are relatively few studies on the application of the NEZHA model to Microblog sentiment analysis during the epidemic, and the validity of the model in this field is still lacking. In response to this problem, the NEZHA model was used to import the 2020 Microblog dataset for sentiment analysis and prediction to verify its effectiveness. Through experimental verification, the NEZHA model has significantly improved the Macro F1 value for microblog sentiment analysis compared with the BERT model, which has greater practical value.

Copyright
© 2022 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

Volume Title
Proceedings of the 2022 International Conference on Computer Science, Information Engineering and Digital Economy (CSIEDE 2022)
Series
Advances in Computer Science Research
Publication Date
30 December 2022
ISBN
978-94-6463-108-1
ISSN
2352-538X
DOI
10.2991/978-94-6463-108-1_42How to use a DOI?
Copyright
© 2022 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

TY  - CONF
AU  - Fan Yang
PY  - 2022
DA  - 2022/12/30
TI  - Sentiment Analysis of Microblog During the COVID-19 Pandemic Based on NEZHA Model
BT  - Proceedings of the 2022 International Conference on Computer Science, Information Engineering and Digital Economy (CSIEDE 2022)
PB  - Atlantis Press
SP  - 369
EP  - 375
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-108-1_42
DO  - 10.2991/978-94-6463-108-1_42
ID  - Yang2022
ER  -