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
  • [31] Du Y, Liu D, Morente-Molinera J A, Et al., A data-driven method for user satisfaction evaluation of smart and connected products, Expert Systems with Applications, 210, 3, (2022)
  • [32] Li Y, Zhang Y, Xu Z., A decision-making model under probabilistic linguistic circumstances with unknown criteria weights for online customer reviews[J], International Journal of Fuzzy Systems, 22, 3, pp. 777-789, (2020)
  • [33] Du Y, Liu D, Duan H., A textual data-driven method to identify and prioritise user preferences based on regret/rejoicing perception for smart and connected products[J], International Journal of Production Research, 60, 13, pp. 4176-4196, (2022)
  • [34] Malarkodi C S, Lex E, Devi S L., Named entity recognition for the agricultural domain[J], Research in Computing Science, 117, 1, pp. 121-132, (2016)
  • [35] Min L, Miao X, Bi P, Et al., A small amount of labeled data Chinese online course review target extraction via ALBERT-IDCNN-CRF model, Journal of Physics: Conference Series, 1651, 1, (2020)
  • [36] Zaremba W, Sutskever I, Vinyals O., Recurrent neural network regularization, Eprint Arxiv, (2014)
  • [37] Chua L O, Roska T., The CNN paradigm[J], IEEE Transactions on Circuits & Systems I: Fundamental Theory & Applications, 40, 3, pp. 147-156, (1993)
  • [38] Colon-Ruiz C, Segura-Bedmar I., Comparing deep learning architectures for sentiment analysis on drug reviews, Journal of Biomedical Informatics, 110, (2020)
  • [39] Graves A, Schmidhuber J., Framewise phoneme classification with bidirectional LSTM and other neural network architectures[J], Neural Networks, 18, 5–6, pp. 602-610, (2005)
  • [40] Sara R, Preslav N, Svetlana K, Et al., SemEval-2015 task 10: Sentiment analysis in Twitter[C], Proceedings of the 9th International Workshop on Semantic Evaluation, pp. 451-463, (2015)
123456