Data Augmentation Using BERT-Based Models for Aspect-Based Sentiment Analysis

被引:0
|
作者
Hollander, Bron [1 ]
Frasincar, Flavius [1 ]
van der Knaap, Finn [1 ]
机构
[1] Erasmus Univ, Burgemeester Oudlaan 50, NL-3062 PA Rotterdam, Netherlands
来源
WEB ENGINEERING, ICWE 2024 | 2024年 / 14629卷
关键词
Aspect-based sentiment classification; Data augmentation; Neural network; Pre-trained language model;
D O I
10.1007/978-3-031-62362-2_8
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In today's digital world, there is an overwhelming amount of opinionated data on the Web. However, effectively analyzing all available data proves to be a resource-intensive endeavor, requiring substantial time and financial investments to curate high-quality training datasets. To mitigate such problems, this paper compares data augmentation models for aspect-based sentiment analysis. Specifically, we analyze the effect of several BERT-based data augmentation methods on the performance of the state-of-the-art HAABSA++ model. We consider the following data augmentation models: EDA-adjusted (baseline), BERT, Conditional-BERT, BERTprepend, and BERTexpand. Our findings show that incorporating data augmentation techniques can significantly improve the out-of-sample accuracy of the HAABSA++ model. Specifically, our results highlight the effectiveness of BERTprepend and BERTexpand, increasing the test accuracy from 78.56% to 79.23% and from 82.62% to 84.47% for the SemEval 2015 and SemEval 2016 datasets, respectively.
引用
收藏
页码:115 / 122
页数:8
相关论文
共 50 条
  • [41] Exploring ChatGPT-Based Augmentation Strategies for Contrastive Aspect-Based Sentiment Analysis
    Xu, Lingling
    Xie, Haoran
    Qin, S. Joe
    Wang, Fu Lee
    Tao, Xiaohui
    IEEE INTELLIGENT SYSTEMS, 2025, 40 (01) : 69 - 76
  • [42] Sentiment Analysis of Customer Comments in Banking using BERT-based Approaches
    Masarifoglu, Melik
    Tigrak, Umit
    Hakyemez, Sefa
    Gul, Guven
    Bozan, Erdal
    Buyuklu, Ali Hakan
    Ozgur, Arzucan
    29TH IEEE CONFERENCE ON SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS (SIU 2021), 2021,
  • [43] EASE: An enhanced active learning framework for aspect-based sentiment analysis based on sample diversity and data augmentation
    Alturayeif, Nouf
    Ahmad, Irfan
    EXPERT SYSTEMS WITH APPLICATIONS, 2025, 261
  • [44] A Challenge Dataset and Effective Models for Aspect-Based Sentiment Analysis
    Jiang, Qingnan
    Chen, Lei
    Xu, Ruifeng
    Ao, Xiang
    Yang, Min
    2019 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING AND THE 9TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING (EMNLP-IJCNLP 2019): PROCEEDINGS OF THE CONFERENCE, 2019, : 6280 - 6285
  • [45] Bert-based graph unlinked embedding for sentiment analysis
    Jin, Youkai
    Zhao, Anping
    COMPLEX & INTELLIGENT SYSTEMS, 2024, 10 (02) : 2627 - 2638
  • [46] An Efficient Long Chinese Text Sentiment Analysis Method Using BERT-Based Models with BiGRU
    Sheng, Deming
    Yuan, Jingling
    PROCEEDINGS OF THE 2021 IEEE 24TH INTERNATIONAL CONFERENCE ON COMPUTER SUPPORTED COOPERATIVE WORK IN DESIGN (CSCWD), 2021, : 192 - 197
  • [47] Enhancing BERT Representation With Context-Aware Embedding for Aspect-Based Sentiment Analysis
    Li, Xinlong
    Fu, Xingyu
    Xu, Guangluan
    Yang, Yang
    Wang, Jiuniu
    Jin, Li
    Liu, Qing
    Xiang, Tianyuan
    IEEE ACCESS, 2020, 8 : 46868 - 46876
  • [48] tRF-BERT: A transformative approach to aspect-based sentiment analysis in the bengali language
    Ahmed, Shihab
    Samia, Moythry Manir
    Sayma, Maksuda Haider
    Kabir, Md. Mohsin
    Mridha, M. F.
    PLOS ONE, 2024, 19 (09):
  • [49] Aspect-based Sentiment Analysis for Bengali Text using Bidirectional Encoder Representations from Transformers (BERT)
    Samia, Moythry Manir
    Rajee, Alimul
    Hasan, Md Rakib
    Faruq, Mohammad Omar
    Paul, Pintu Chandra
    INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2022, 13 (12) : 978 - 986
  • [50] BERT-Based Sentiment Analysis: A Software Engineering Perspective
    Batra, Himanshu
    Punn, Narinder Singh
    Sonbhadra, Sanjay Kumar
    Agarwal, Sonali
    DATABASE AND EXPERT SYSTEMS APPLICATIONS, DEXA 2021, PT I, 2021, 12923 : 138 - 148