Sentiment Analysis of Political Posts on Hong Kong Local Forums Using Fine-Tuned mBERT

Guanrong Li; Ziwei Wang; Minzhu Zhao; Yunya Song; Liang Lan

doi:10.1109/BigData55660.2022.10020704

Sentiment Analysis of Political Posts on Hong Kong Local Forums Using Fine-Tuned mBERT

Guanrong Li, Ziwei Wang, Minzhu Zhao, Yunya Song, Liang Lan^*

^*Corresponding author for this work

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

3 Citations (Scopus)

Abstract

Sentiment analysis is an important and challenging task in natural language processing. It has been studied for a few decades. Recently, Bidirectional Encoder Representations from Transformer (BERT) model has been introduced to tackle this task and gain very promising results. However, most existing studies on fine-tuning BERT models for sentiment analysis focus on high-resource language (e.g., En-glish or Mandarin). This paper studies the sentiment analysis of Cantonese political posts on Hong Kong local forums. We first collected and labeled posts related to Anti-Extradition Law Amendment Bill (Anti-ELAB) movement in Hong Kong discussion forums. We then examined the performance of dictionary-based sentiment analysis, traditional machine learning-based, fine-tuned BERT and fine-tuned multilingual BERT (mBERT) models. Our results show that fine-tuned mBERT model achieves the best performance on our collected and labeled Cantonese dataset.

Original language	English
Title of host publication	Proceedings - 2022 IEEE International Conference on Big Data, Big Data 2022
Editors	Shusaku Tsumoto, Yukio Ohsawa, Lei Chen, Dirk Van den Poel, Xiaohua Hu, Yoichi Motomura, Takuya Takagi, Lingfei Wu, Ying Xie, Akihiro Abe, Vijay Raghavan
Publisher	IEEE
Pages	6763-6765
Number of pages	3
ISBN (Electronic)	9781665480451
ISBN (Print)	9781665480468
DOIs	https://doi.org/10.1109/BigData55660.2022.10020704
Publication status	Published - Dec 2022
Event	2022 IEEE International Conference on Big Data, Big Data 2022 - Osaka, Japan Duration: 17 Dec 2022 → 20 Dec 2022 https://ieeexplore.ieee.org/xpl/conhome/10020192/proceeding

Publication series

Name	Proceedings - IEEE International Conference on Big Data

Conference

Conference	2022 IEEE International Conference on Big Data, Big Data 2022
Country/Territory	Japan
City	Osaka
Period	17/12/22 → 20/12/22
Internet address	https://ieeexplore.ieee.org/xpl/conhome/10020192/proceeding

Scopus Subject Areas

Modelling and Simulation
Computer Networks and Communications
Information Systems
Information Systems and Management
Safety, Risk, Reliability and Quality
Control and Optimization

User-Defined Keywords

BERT
Fine-tuned BERT
multilingual BERT
Sentiment Analysis

Access to Document

10.1109/BigData55660.2022.10020704

Cite this

Li, G., Wang, Z., Zhao, M., Song, Y., & Lan, L. (2022). Sentiment Analysis of Political Posts on Hong Kong Local Forums Using Fine-Tuned mBERT. In S. Tsumoto, Y. Ohsawa, L. Chen, D. Van den Poel, X. Hu, Y. Motomura, T. Takagi, L. Wu, Y. Xie, A. Abe, & V. Raghavan (Eds.), Proceedings - 2022 IEEE International Conference on Big Data, Big Data 2022 (pp. 6763-6765). (Proceedings - IEEE International Conference on Big Data). IEEE. https://doi.org/10.1109/BigData55660.2022.10020704

Li, Guanrong ; Wang, Ziwei ; Zhao, Minzhu et al. / Sentiment Analysis of Political Posts on Hong Kong Local Forums Using Fine-Tuned mBERT. Proceedings - 2022 IEEE International Conference on Big Data, Big Data 2022. editor / Shusaku Tsumoto ; Yukio Ohsawa ; Lei Chen ; Dirk Van den Poel ; Xiaohua Hu ; Yoichi Motomura ; Takuya Takagi ; Lingfei Wu ; Ying Xie ; Akihiro Abe ; Vijay Raghavan. IEEE, 2022. pp. 6763-6765 (Proceedings - IEEE International Conference on Big Data).

@inproceedings{1c7c7203a8874594b22cd857b0323bc0,

title = "Sentiment Analysis of Political Posts on Hong Kong Local Forums Using Fine-Tuned mBERT",

abstract = "Sentiment analysis is an important and challenging task in natural language processing. It has been studied for a few decades. Recently, Bidirectional Encoder Representations from Transformer (BERT) model has been introduced to tackle this task and gain very promising results. However, most existing studies on fine-tuning BERT models for sentiment analysis focus on high-resource language (e.g., En-glish or Mandarin). This paper studies the sentiment analysis of Cantonese political posts on Hong Kong local forums. We first collected and labeled posts related to Anti-Extradition Law Amendment Bill (Anti-ELAB) movement in Hong Kong discussion forums. We then examined the performance of dictionary-based sentiment analysis, traditional machine learning-based, fine-tuned BERT and fine-tuned multilingual BERT (mBERT) models. Our results show that fine-tuned mBERT model achieves the best performance on our collected and labeled Cantonese dataset.",

keywords = "BERT, Fine-tuned BERT, multilingual BERT, Sentiment Analysis",

author = "Guanrong Li and Ziwei Wang and Minzhu Zhao and Yunya Song and Liang Lan",

note = "Funding Information: The research was supported by a General Research Fund grant (HKBU 12605520) of the Research Grant Council of Hong Kong, the Public Policy Research Funding Scheme (2021.A2.047.21B) from Policy Innovation and Co-ordination Office of the Hong Kong Special Administrative Region Government, and the Interdisciplinary Research Clusters Matching Scheme (IRCMS/19-20/D04), the Initiation Grant for Faculty Niche Research Areas (RC-FNRA-IG/21-22/COMF/01) of HKBU, and the AIS Scheme (AIS 21-22/01) and CMC Scheme (CMC/21-22/003) from School of Communication, HKBU, and the Natural Science Foundation Council of China (61906161). Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 IEEE International Conference on Big Data, Big Data 2022 ; Conference date: 17-12-2022 Through 20-12-2022",

year = "2022",

month = dec,

doi = "10.1109/BigData55660.2022.10020704",

language = "English",

isbn = "9781665480468",

series = "Proceedings - IEEE International Conference on Big Data",

publisher = "IEEE",

pages = "6763--6765",

editor = "Shusaku Tsumoto and Yukio Ohsawa and Lei Chen and {Van den Poel}, Dirk and Xiaohua Hu and Yoichi Motomura and Takuya Takagi and Lingfei Wu and Ying Xie and Akihiro Abe and Vijay Raghavan",

booktitle = "Proceedings - 2022 IEEE International Conference on Big Data, Big Data 2022",

address = "United States",

url = "https://ieeexplore.ieee.org/xpl/conhome/10020192/proceeding",

}

Li, G, Wang, Z, Zhao, M, Song, Y & Lan, L 2022, Sentiment Analysis of Political Posts on Hong Kong Local Forums Using Fine-Tuned mBERT. in S Tsumoto, Y Ohsawa, L Chen, D Van den Poel, X Hu, Y Motomura, T Takagi, L Wu, Y Xie, A Abe & V Raghavan (eds), Proceedings - 2022 IEEE International Conference on Big Data, Big Data 2022. Proceedings - IEEE International Conference on Big Data, IEEE, pp. 6763-6765, 2022 IEEE International Conference on Big Data, Big Data 2022, Osaka, Japan, 17/12/22. https://doi.org/10.1109/BigData55660.2022.10020704

Sentiment Analysis of Political Posts on Hong Kong Local Forums Using Fine-Tuned mBERT. / Li, Guanrong; Wang, Ziwei; Zhao, Minzhu et al.
Proceedings - 2022 IEEE International Conference on Big Data, Big Data 2022. ed. / Shusaku Tsumoto; Yukio Ohsawa; Lei Chen; Dirk Van den Poel; Xiaohua Hu; Yoichi Motomura; Takuya Takagi; Lingfei Wu; Ying Xie; Akihiro Abe; Vijay Raghavan. IEEE, 2022. p. 6763-6765 (Proceedings - IEEE International Conference on Big Data).

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

TY - GEN

T1 - Sentiment Analysis of Political Posts on Hong Kong Local Forums Using Fine-Tuned mBERT

AU - Li, Guanrong

AU - Wang, Ziwei

AU - Zhao, Minzhu

AU - Song, Yunya

AU - Lan, Liang

N1 - Funding Information: The research was supported by a General Research Fund grant (HKBU 12605520) of the Research Grant Council of Hong Kong, the Public Policy Research Funding Scheme (2021.A2.047.21B) from Policy Innovation and Co-ordination Office of the Hong Kong Special Administrative Region Government, and the Interdisciplinary Research Clusters Matching Scheme (IRCMS/19-20/D04), the Initiation Grant for Faculty Niche Research Areas (RC-FNRA-IG/21-22/COMF/01) of HKBU, and the AIS Scheme (AIS 21-22/01) and CMC Scheme (CMC/21-22/003) from School of Communication, HKBU, and the Natural Science Foundation Council of China (61906161). Publisher Copyright: © 2022 IEEE.

PY - 2022/12

Y1 - 2022/12

N2 - Sentiment analysis is an important and challenging task in natural language processing. It has been studied for a few decades. Recently, Bidirectional Encoder Representations from Transformer (BERT) model has been introduced to tackle this task and gain very promising results. However, most existing studies on fine-tuning BERT models for sentiment analysis focus on high-resource language (e.g., En-glish or Mandarin). This paper studies the sentiment analysis of Cantonese political posts on Hong Kong local forums. We first collected and labeled posts related to Anti-Extradition Law Amendment Bill (Anti-ELAB) movement in Hong Kong discussion forums. We then examined the performance of dictionary-based sentiment analysis, traditional machine learning-based, fine-tuned BERT and fine-tuned multilingual BERT (mBERT) models. Our results show that fine-tuned mBERT model achieves the best performance on our collected and labeled Cantonese dataset.

AB - Sentiment analysis is an important and challenging task in natural language processing. It has been studied for a few decades. Recently, Bidirectional Encoder Representations from Transformer (BERT) model has been introduced to tackle this task and gain very promising results. However, most existing studies on fine-tuning BERT models for sentiment analysis focus on high-resource language (e.g., En-glish or Mandarin). This paper studies the sentiment analysis of Cantonese political posts on Hong Kong local forums. We first collected and labeled posts related to Anti-Extradition Law Amendment Bill (Anti-ELAB) movement in Hong Kong discussion forums. We then examined the performance of dictionary-based sentiment analysis, traditional machine learning-based, fine-tuned BERT and fine-tuned multilingual BERT (mBERT) models. Our results show that fine-tuned mBERT model achieves the best performance on our collected and labeled Cantonese dataset.

KW - BERT

KW - Fine-tuned BERT

KW - multilingual BERT

KW - Sentiment Analysis

UR - http://www.scopus.com/inward/record.url?scp=85147966552&partnerID=8YFLogxK

U2 - 10.1109/BigData55660.2022.10020704

DO - 10.1109/BigData55660.2022.10020704

M3 - Conference proceeding

AN - SCOPUS:85147966552

SN - 9781665480468

T3 - Proceedings - IEEE International Conference on Big Data

SP - 6763

EP - 6765

BT - Proceedings - 2022 IEEE International Conference on Big Data, Big Data 2022

A2 - Tsumoto, Shusaku

A2 - Ohsawa, Yukio

A2 - Chen, Lei

A2 - Van den Poel, Dirk

A2 - Hu, Xiaohua

A2 - Motomura, Yoichi

A2 - Takagi, Takuya

A2 - Wu, Lingfei

A2 - Xie, Ying

A2 - Abe, Akihiro

A2 - Raghavan, Vijay

PB - IEEE

T2 - 2022 IEEE International Conference on Big Data, Big Data 2022

Y2 - 17 December 2022 through 20 December 2022

ER -

Li G, Wang Z, Zhao M, Song Y , Lan L. Sentiment Analysis of Political Posts on Hong Kong Local Forums Using Fine-Tuned mBERT. In Tsumoto S, Ohsawa Y, Chen L, Van den Poel D, Hu X, Motomura Y, Takagi T, Wu L, Xie Y, Abe A, Raghavan V, editors, Proceedings - 2022 IEEE International Conference on Big Data, Big Data 2022. IEEE. 2022. p. 6763-6765. (Proceedings - IEEE International Conference on Big Data). doi: 10.1109/BigData55660.2022.10020704

Sentiment Analysis of Political Posts on Hong Kong Local Forums Using Fine-Tuned mBERT

Abstract

Publication series

Conference

Scopus Subject Areas

User-Defined Keywords

Access to Document

Other files and links

Fingerprint

Cite this