p-Norm Broad Learning for Negative Emotion Classification in Social Networks

Negative emotion classification refers to the automatic classification of negative emotion of texts in social networks. Most existing methods are based on deep learning models, facing challenges such as complex structures and too many hyperparameters. To meet these challenges, in this paper, we prop...

Full description

Saved in:
Bibliographic Details
Main Authors: Guanghao Chen, Sancheng Peng, Rong Zeng, Zhongwang Hu, Lihong Cao, Yongmei Zhou, Zhouhao Ouyang, Xiangyu Nie
Format: Article
Language:English
Published: Tsinghua University Press 2022-09-01
Series:Big Data Mining and Analytics
Subjects:
Online Access:https://www.sciopen.com/article/10.26599/BDMA.2022.9020008
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832572815239282688
author Guanghao Chen
Sancheng Peng
Rong Zeng
Zhongwang Hu
Lihong Cao
Yongmei Zhou
Zhouhao Ouyang
Xiangyu Nie
author_facet Guanghao Chen
Sancheng Peng
Rong Zeng
Zhongwang Hu
Lihong Cao
Yongmei Zhou
Zhouhao Ouyang
Xiangyu Nie
author_sort Guanghao Chen
collection DOAJ
description Negative emotion classification refers to the automatic classification of negative emotion of texts in social networks. Most existing methods are based on deep learning models, facing challenges such as complex structures and too many hyperparameters. To meet these challenges, in this paper, we propose a method for negative emotion classification utilizing a Robustly Optimized BERT Pretraining Approach (RoBERTa) and p-norm Broad Learning (p-BL). Specifically, there are mainly three contributions in this paper. Firstly, we fine-tune the RoBERTa to adapt it to the task of negative emotion classification. Then, we employ the fine-tuned RoBERTa to extract features of original texts and generate sentence vectors. Secondly, we adopt p-BL to construct a classifier and then predict negative emotions of texts using the classifier. Compared with deep learning models, p-BL has advantages such as a simple structure that is only 3-layer and fewer parameters to be trained. Moreover, it can suppress the adverse effects of more outliers and noise in data by flexibly changing the value of p. Thirdly, we conduct extensive experiments on the public datasets, and the experimental results show that our proposed method outperforms the baseline methods on the tested datasets.
format Article
id doaj-art-7738573bcd0a4c4184931530c7538dc3
institution Kabale University
issn 2096-0654
language English
publishDate 2022-09-01
publisher Tsinghua University Press
record_format Article
series Big Data Mining and Analytics
spelling doaj-art-7738573bcd0a4c4184931530c7538dc32025-02-02T06:50:33ZengTsinghua University PressBig Data Mining and Analytics2096-06542022-09-015324525610.26599/BDMA.2022.9020008p-Norm Broad Learning for Negative Emotion Classification in Social NetworksGuanghao Chen0Sancheng Peng1Rong Zeng2Zhongwang Hu3Lihong Cao4Yongmei Zhou5Zhouhao Ouyang6Xiangyu Nie7Laboratory of Language Engineering and Computing, Guangdong University of Foreign Studies, Guangzhou 510006, ChinaLaboratory of Language Engineering and Computing, Guangdong University of Foreign Studies, Guangzhou 510006, ChinaGuangdong Provincial Key Laboratory of Nanophotonic Functional Materials and Devices, South China Normal University, Guangzhou 511400, ChinaSchool of Computer Science and Software, Zhaoqing University, Zhaoqing 526000, ChinaLaboratory of Language Engineering and Computing, Guangdong University of Foreign Studies, Guangzhou 510006, ChinaSchool of Information Science and Technology, Guangdong University of Foreign Studies, Guangzhou 510006, ChinaSchool of Computing, University of Leeds, Leeds LS2 9JT, United KingdomSchool of Information Science and Technology, Guangdong University of Foreign Studies, Guangzhou 510006, ChinaNegative emotion classification refers to the automatic classification of negative emotion of texts in social networks. Most existing methods are based on deep learning models, facing challenges such as complex structures and too many hyperparameters. To meet these challenges, in this paper, we propose a method for negative emotion classification utilizing a Robustly Optimized BERT Pretraining Approach (RoBERTa) and p-norm Broad Learning (p-BL). Specifically, there are mainly three contributions in this paper. Firstly, we fine-tune the RoBERTa to adapt it to the task of negative emotion classification. Then, we employ the fine-tuned RoBERTa to extract features of original texts and generate sentence vectors. Secondly, we adopt p-BL to construct a classifier and then predict negative emotions of texts using the classifier. Compared with deep learning models, p-BL has advantages such as a simple structure that is only 3-layer and fewer parameters to be trained. Moreover, it can suppress the adverse effects of more outliers and noise in data by flexibly changing the value of p. Thirdly, we conduct extensive experiments on the public datasets, and the experimental results show that our proposed method outperforms the baseline methods on the tested datasets.https://www.sciopen.com/article/10.26599/BDMA.2022.9020008social networksnegative emotionrobertabroad learningp-norm
spellingShingle Guanghao Chen
Sancheng Peng
Rong Zeng
Zhongwang Hu
Lihong Cao
Yongmei Zhou
Zhouhao Ouyang
Xiangyu Nie
p-Norm Broad Learning for Negative Emotion Classification in Social Networks
Big Data Mining and Analytics
social networks
negative emotion
roberta
broad learning
p-norm
title p-Norm Broad Learning for Negative Emotion Classification in Social Networks
title_full p-Norm Broad Learning for Negative Emotion Classification in Social Networks
title_fullStr p-Norm Broad Learning for Negative Emotion Classification in Social Networks
title_full_unstemmed p-Norm Broad Learning for Negative Emotion Classification in Social Networks
title_short p-Norm Broad Learning for Negative Emotion Classification in Social Networks
title_sort p norm broad learning for negative emotion classification in social networks
topic social networks
negative emotion
roberta
broad learning
p-norm
url https://www.sciopen.com/article/10.26599/BDMA.2022.9020008
work_keys_str_mv AT guanghaochen pnormbroadlearningfornegativeemotionclassificationinsocialnetworks
AT sanchengpeng pnormbroadlearningfornegativeemotionclassificationinsocialnetworks
AT rongzeng pnormbroadlearningfornegativeemotionclassificationinsocialnetworks
AT zhongwanghu pnormbroadlearningfornegativeemotionclassificationinsocialnetworks
AT lihongcao pnormbroadlearningfornegativeemotionclassificationinsocialnetworks
AT yongmeizhou pnormbroadlearningfornegativeemotionclassificationinsocialnetworks
AT zhouhaoouyang pnormbroadlearningfornegativeemotionclassificationinsocialnetworks
AT xiangyunie pnormbroadlearningfornegativeemotionclassificationinsocialnetworks