Fine-grained sentiment analysis of online reviews based on RoBERTa-BiLSTM-CRF

被引：0
|
作者：
Xu J. [1 ]
Zhang J. [1 ,2 ]
Song L. [1 ]
Gao Y. [1 ]
机构：
[1] School of Data Science and Artificial Intelligence, Dongbei University of Finance and Economics, Dalian
[2] School of Hotel and Tourism Management, The Hong Kong Polytechnic University, Hong Kong
来源：
Xitong Gongcheng Lilun yu Shijian/System Engineering Theory and Practice | 2023年 / 43卷 / 12期
基金：
中国国家社会科学基金; 中国国家自然科学基金;
关键词：
combined model; emotional intensity; fine-grained sentiment analysis; online reviews;
D O I：
10.12011/SETP2022-2001
中图分类号：
学科分类号：
摘要：
In the context of the rapid development of e-commerce, the commercial value of online reviews has become increasingly prominent. The methods of the sentiment analysis of users generated online reviews has shifted from coarse-grained sentiment analysis at sentence or paragraph level to fine-grained sentiment analysis at attribution level. However, the current fine-grained sentiment analysis methods have limitations in the sentiment factors identification task, such as polysemy, underutilization of context semantics, and ignorance of the constraint condition between labels. Meanwhile, the quantification methods of measuring the attribute-oriented sentiment intensity does not fully consider grammatical information. In this regard, this paper proposes a hybrid fine-grained sentiment analysis method, RoBERTa-BiLSTM-CRF, which can effectively solve the above problems. This method can accurately quantify the attributes-oriented sentiment intensity of products or services evaluated by users in online reviews, and effectively quantify the sentiment strength of user feedback by combining sentiment triplet and grammatical information. In order to evaluate the effect of the proposed method, groups of comparative experiments and ablation experiments were conducted on the datasets from multiple fields, including hotel online reviews, Meituan takeaway online reviews and the CLUENER2020 dataset. The experimental results show that, compared with the state-of-the-art models, the RoBERTa-BiLSTM-CRF model used in this paper has obtained the best F1 score in the experiments of sentiment element identification on all datasets, and the quantification methods of measuring the attribute-oriented sentiment intensity proposed in this paper is more accuracy, which can better reflect the continuity of human emotion. In addition, the ablation experiments further demonstrate the importance of each structure of the fusion model. © 2023 Systems Engineering Society of China. All rights reserved.
引用
下载
收藏
页码：3519 / 3535
页数：16
相关论文
共 52 条
  • [1] Jin L, Zheng B R., Optimal self-operated channel introduction strategy for E-commerce platform: Value of the online reviews[J], Systems Engineering — Theory & Practice, 43, 2, pp. 469-487, (2023)
  • [2] Guo X D, Na R S, Cui S Z., Consumer reviews sentiment analysis based on CNN-BiLSTM [J], Systems Engineering — Theory & Practice, 40, 3, pp. 653-663, (2020)
  • [3] Chou S Y., Online reviews and pre-purchase cognitive dissonance: A theoretical framework and research propositions[J], Journal of Emerging Trends in Computing & Information Sciences, 3, 2, pp. 419-424, (2012)
  • [4] Liu Q B, Karahanna E., The dark side of reviews: The swaying effects of online product reviews on attribute preference construction[J], MIS Quarterly: Management Information Systems, 41, 2, pp. 427-448, (2017)
  • [5] Pang B, Lee L, Vaithyanathan S., Thumbs up sentiment classification using machine learning techniques[C], Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 79-86, (2002)
  • [6] Van de Kauter M, Breesch D, Hoste V., Fine-grained analysis of explicit and implicit sentiment in financial news articles[J], Expert Systems with applications, 42, 11, pp. 4999-5010, (2015)
  • [7] Zhang J, Zhang A, Liu D, Et al., Customer preferences extraction for air purifiers based on fine-grained sentiment analysis of online reviews, Knowledge-Based Systems, 228, (2021)
  • [8] Jin W, Ho H H, Srihari R K., OpinionMiner: A novel machine learning system for web opinion mining and extraction[C], Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1195-1204, (2009)
  • [9] McCallum A, Freitag D, Pereira F C N., Maximum entropy Markov models for information extraction and segmentation[C], International Conference on Machine Learning, 17, 2000, pp. 591-598, (2000)
  • [10] Lafferty J, McCallum A, Pereira F., Conditional random fields: Probabilistic models for segmenting and labeling sequence data[C], Proceedings of International Conference Machine Learning, pp. 282-289, (2001)
123456