基于TextCRNN-OvR的患者咨询文本分类方法
Patient Consultation Text Classification Method Based on TextCRNN-OvR
摘要: 人工智能技术加速了互联网医疗发展，患者在线问诊逐渐成为新趋势。然而大多数患者自身医学知识匮乏，往往出现挂错科室的情况。因此，患者咨询文本分类对于引导患者线上选择就诊科室显得十分重要。本文提出一种结合卷积循环神经网络与OvR策略的文本多分类方法，既可以捕捉文本局部特征，又可以学习词序信息。本文爬取了39问答网上的患者咨询文本作为数据源，对所提方法进行了验证，并与已有的分类算法作对比，结果表明所提方法在精度、召回率、F1值及准确率指标上具有更优越的算法性能。其中，相较于其他SOTA的文本分类模型，TextCRNN-OvR在文本分类精度上取得了1%~4%不同程度上的提高，这进一步说明了TextCRNN在提取文本特征方面以及本文OvR多分类策略的有效性。
Abstract: The development of Internet medical treatment has been accelerated by artificial intelligence technology, then online patient consultation is becoming a new trend. However, most patients often choose the wrong department due to a lack of adequate medical expertise. Therefore, the classification of patient consultation text is very important for guiding patients to choose departments online. This paper proposes a text multiple classification method combining the convolutional recurrent neural network and OvR strategy, which can capture local features of text but also learn word order information. In this paper, the proposed method is verified by crawling the patient consultation text on 39ask.com as the data source. Compared with existing classification algorithms, the results show that the proposed method has better performance in terms of precision, recall rate, F1 score and accuracy. Among them, compared with other SOTA text classification models, TextCRNN-OvR has improved the accuracy of text classification by 1% to 4% to varying degrees, which further illustrates the advantages of TextCRNN in extracting text features and the effectiveness of the OvR multi-classification strategy in this paper.
文章引用：张远芳. 基于TextCRNN-OvR的患者咨询文本分类方法[J]. 运筹与模糊学, 2023, 13(2): 1166-1175. https://doi.org/10.12677/ORF.2023.132120

参考文献

[1] 王若佳, 张璐, 王继民. 基于机器学习的在线问诊平台智能分诊研究[J]. 数据分析与知识发现, 2019, 3(9): 88-97.
[2] 何炎祥, 孙松涛, 牛菲菲, 李飞. 用于微博情感分析的一种情感语义增强的深度学习模型[J]. 计算机学报, 2017, 40(4): 773-790.
[3] Abdi, A., Shamsuddin, S.M., Hasan, S., et al. (2019) Deep Learning-Based Sentiment Classification of Evaluative Text Based on Multi-Feature Fusion. Information Processing and Man-agement, 56, 1245-1259. [Google Scholar] [CrossRef] 
[4] Zhou, C., Sun, C., Liu, Z., et al. (2015) A C-LSTM Neural Network for Text Classification. Computer Science, 1, 39-44.
[5] Kim, Y. (2014) Convolutional Neural Networks for Sentence Classification. Proceedings of the Conference on Empirical Methods in Natural Language Processing, Stroudsburg, 26-28 October 2014, 1746-1751. [Google Scholar] [CrossRef] 
[6] Kalchbrenner, N., Grefenstette, E. and Blunsom, P. (2014) A Convolutional Network for Modeling Sentences. Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, Volume 1, 655-665. [Google Scholar] [CrossRef] 
[7] Xiao, Y. and Cho, K. (2016) Efficient Character-Level Document Classification by Combining Convolution and Recurrent Layers.
[8] Huang, X., Qiao, L., Yu, W., et al. (2020) End-to-End Sequence Labeling via Convolutional Recurrent Neural Network with a Connectionist Temporal Clas-sification Layer. International Journal of Computational Intelligence Systems, 13, 341-351. [Google Scholar] [CrossRef] 
[9] Hochreiter, S. and Schmidhuber, J. (1997) Long Short-Term Memory. Neural Computation, 9, 1735-1780. [Google Scholar] [CrossRef] [PubMed]
[10] Cho, K., Van Merrienboer, B., Gulcehre, C., et al. (2014) Learning Phrase Representations Using RNN Encoder-Decoder for Statistical Machine Translation. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, October 2014, 1724-1734. [Google Scholar] [CrossRef] 
[11] 王伟, 孙玉霞, 齐庆杰, 孟祥福. 基于BiGRU-attention神经网络的文本情感分类模型[J]. 计算机应用研究, 2019, 36(12): 3558-3564.
[12] Han, Y., Liu, M. and Jing, W. (2020) Aspect-Level Drug Reviews Sentiment Analysis Based on Double BiGRU and Knowledge Transfer. IEEE Access, 8, 21314-21325. [Google Scholar] [CrossRef] 
[13] Shilaskar, S., Ghatol, A. and Chatur, P. (2017) Medical Decision Support System for Extremely Imbalanced Datasets. Information Sciences, 384, 205-219. [Google Scholar] [CrossRef] 
[14] Zhou, P., Qi, Z., Zheng, S., et al. (2016) Text Classification Improved by Integrating Bidirectional LSTM with Two Dimensional Max Pooling.
[15] Kingma, D.P. and Ba, J.L. (2015) Adam: A Method for Stochastic Optimization. Proceedings of the 3rd International Conference on Learning Representations (ICLR 2015), San Diego, 7-9 May 2015. arXiv:1412.6980

为你推荐