All Title Author
Keywords Abstract

Publish in OALib Journal
ISSN: 2333-9721
APC: Only $99

ViewsDownloads

Relative Articles

More...

基于RoBerta-BiGRU-Attention的景区评论情感分析研究——以沈阳市为例
Research on Sentiment Analysis of Scenic Area Comments Based on RoBerta-BiGRU-Attention—Taking Shenyang as an Example

DOI: 10.12677/HJDM.2023.134031, PP. 312-326

Keywords: RoBerta词向量,BiGRU,注意力机制,情感分析,潜在狄利克雷分布
RoBerta Word Vector
, BiGRU, Attention Mechanism, Sentiment Analysis, Latent Dirichlet Allocation

Full-Text   Cite this paper   Add to My Lib

Abstract:

游客在评论中所表达的意见和感受,能够直观地反映他们对旅游目的地的评价,同时语气鲜明、情感强烈。由此带来的巨大而动态的信息空间需要消费者和产品/服务提供者共同理解和导航。针对目前景区在线评论文本情感分类准确性不高的问题,提出一种基于RoBerta词向量和双向门控循环单元(BiGRU)的改进模型,使用能够表征文本丰富语义特征的Roberta模型进行词向量表示,结合能够长期保留文本上下文关联信息的BiGRU神经网络提高模型的分类效果,并在此基础上引入注意力(Attention)机制,突出文本中更能表达分类结果的情感词权重,提高情感分类的准确率。将上述模型分别在沈阳市3个景区评论数据上进行情感极性分类和预测,实验结果表明,该模型在各数据集上都获得了良好的性能。同时结合LDA主题模型分析,得到游客评论的期望和诉求,为沈阳市旅游业发展提供技术支撑以及未来发展意见。
The opinions and feelings expressed by tourists in the comments can intuitively reflect their evaluation of the tourist destination, and at the same time, the tone is clear and the emotion is strong. The resulting huge and dynamic information space needs to be understood and navigated jointly by consumers and product/service providers. Aiming at the problem of low accuracy of emotion classification in online comment texts of scenic spots, an improved model based on RoBerta word vectors and bidirectional gated recurrent units (BiGRU) is proposed. The Roberta model, which can represent the rich semantic features of texts, is used to represent word vectors. The BiGRU neural network, which can retain text context information for a long time, improves the classification effect of the model. On this basis, an attention mechanism is introduced to highlight the weight of emotional words in the text that can better express the classification results, and improve the accuracy of emotion classification. The above models were used to classify and predict emotional polarity on the comment data of three scenic spots in Shenyang City. The experimental results show that the model has achieved good performance on each data set. At the same time, combined with the LDA topic model analysis, the expectations and appeals of tourists’ comments are obtained, and technical support and future development opinions are provided for the development of Shen- yang’s tourism industry.

References

[1]  Chatterjee, A., et al. (2019) Understanding Emotions in Text Using Deep Learning and Big Data. Computers in Human Behavior, 93, 309-317.
https://doi.org/10.1016/j.chb.2018.12.029
[2]  Rezaeinia, S.M., Rahmani, R., Ghodsi, A., et al. (2018) Sentiment Analysis Based on Improved Pre-trained Word Embeddings. Expert Systems with Applications, 117, 139-147.
https://doi.org/10.1016/j.eswa.2018.08.044
[3]  Hlee, S., Lee, H. and Koo, C. (2018) Hospitality and Tourism Online Review Research: A Systematic Analysis and Heuristic-Systematic Model. Sustainability, 10, Article No. 1141.
https://doi.org/10.3390/su10041141
[4]  Liu, Y. and Hu, H. (2021) Online Review Helpfulness: The Moderating Effects of Review Comprehensiveness. International Journal of Contemporary Hospitality Management, 33, 534-556.
https://doi.org/10.1108/IJCHM-08-2020-0856
[5]  Al-Smadi, M., Qawasmeh, O., Al-Ayyoub, M., et al. (2018) Deep Recurrent Neural Network vs. Support Vector Machine for Aspect-Based Sentiment Analysis of Arabic Hotels’ Reviews. Journal of Computational Science, 27, 386-393.
https://doi.org/10.1016/j.jocs.2017.11.006
[6]  Cho, K., Van Merri?nboer, B., Gulcehre, C., et al. (2014) Learning Phrase Representations Using RNN Encoder-Decoder for Statistical Machine Translation. Proceedings of the 2014 Con-ference on Empirical Methods in Natural Language Processing (EMNLP), Doha, October 2014, 1724-1734.
https://doi.org/10.3115/v1/D14-1179
[7]  Prabha, M.I. and Srikanth, G.U. (2019) Survey of Sentiment Analysis Using Deep Learning Techniques. 2019 IEEE 1st International Conference on Innovations in Information and Commu-nication Technology (ICIICT), Chennai, 25-26 April 2019, 1-9.
https://doi.org/10.1109/ICIICT1.2019.8741438
[8]  Zhou, X., Wan, X. and Xiao, J. (2016) Attention-Based LSTM Network for Cross-Lingual Sentiment Classification. Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, Austin, November 2016, 247- 256.
https://doi.org/10.18653/v1/D16-1024
[9]  Dragoni, M. and Petrucci, G. (2017) A Neural Word Embeddings Ap-proach for Multi-Domain Sentiment Analysis. IEEE Transactions on Affective Computing, 8, 457-470.
https://doi.org/10.1109/TAFFC.2017.2717879
[10]  冯兴杰, 张志伟, 史金钏. 基于卷积神经网络和注意力模型的文本情感分析[J]. 计算机应用研究, 2018, 35(5): 1434-1436.
[11]  Martín, C.A., Torres, J.M., Aguilar, R.M., et al. (2018) Using Deep Learning to Predict Sentiments: Case Study in Tourism. Complexity, 2018, Article ID: 7408431.
https://doi.org/10.1155/2018/7408431
[12]  Devlin, J., Chang, M.W., Lee, K., et al. (2018) Bert: Pre-Training of Deep Bidirectional Transformers for Language Understanding.
[13]  Liu, Y., Ott, M., Goyal, N., et al. (2019) Roberta: A Robustly Optimized Bert Pretraining Approach. arXiv:1907.11692.
[14]  Chi, M., Pan, M. and Wang, W. (2021) Cross Platform Comparative Study of Shared Accommodation and Hotel User Comments: Thematic Social Network and Emo-tion Analysis Based on LDA. Library and Information Work, 65, 107-116.
[15]  Xia, H.S, Li, B.G. and Yang, P. (2016) Topic Extraction in News Comments Based on Improved K-Means Clustering Algorithm. Journal of Infection, 35, 55-65. http://en.cnki.com.cn/Article_en/CJFDTotal-QBXB201601007.htm
[16]  Tang, X.B. and Qiu, X. (2015) Re-search on Topic Oriented High Quality Comment Mining Model. Modern Library and Information Technology, 7, 104-112.
[17]  Tu, H., Tang, X. and Xie, L. (2015) Research on User Requirements Mining Model Based on Online Comments. Journal of Information Technology, 34, 1088-1097.
[18]  Blei, D.M., Ng, A.Y. and Jordan, M.I. (2003) La-tent Dirichlet Allocation. Journal of Machine Learning Research, 3, 993-1022.
[19]  Wu, Y., Na, R. and Li, H. (2021) Representative Negative Comment Extraction Based on Gaussian LDA and Spectral Clustering. Information Sciences, 39, 136-142.
[20]  Ma, Y., Yue, K., Zhang, Z.-C., et al. (2018) Social Media Data Extraction Based on Knowledge Map and LDA Model. Journal of East China Normal University (Natural Science Journal), 5, 183-194. https://xblk.ecnu.edu.cn/EN/Y2018/V2018/I5/183
[21]  Lyu, L.L. and Li, Y.T. (2017) Research on Tourism Information Recommendation—Based on Topic Mining and Presentation of Travel Notes. Modern Intelligence, 37, 61-67. http://en.cnki.com.cn/Article_en/CJFDTOTAL-XDQB201706010.htm
[22]  Pike, S. (2002) Destination Image Analy-sis—A Review of 142 Papers from 1973 to 2000. Tourism Management, 23, 541-549.
https://doi.org/10.1016/S0261-5177(02)00005-5

Full-Text

comments powered by Disqus

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133

WeChat 1538708413