目的/意义 利用人工智能技术从海量评论中迅速甄别负面评论,了解患者的需求与不满,推动远程医疗的可持续发展.方法/过程 以好大夫在线网站的评论数据为例,首先使用双向编码器表征(bidirec-tional encoder representations from transformers,BERT)模型生成词向量,随后将其输入卷积神经网络(conv-olutional neural network,CNN)与双向长短期记忆网络(bidirectional long short-term memory,BiLSTM)构成的双通道模型,最后通过特征融合策略获取文本情感信息,完成二分类任务.结果/结论 该双通道模型能够较好地融合BiLSTM与CNN的优势,与BERT、BERT_BiLSTM、BERT_CNN等9种模型相比,分类准确率、宏F1分数最高,在在线医疗评论文本情感分类任务中具有有效性.
Sentiment Analysis of Online Medical Reviews Based on BERT and Semantics Collaboration through Dual-channel
Purpose/Significance To use artificial intelligence(AI)technology to quickly screen negative comments from a large num-ber of reviews,so as to understand the needs and grievances of patients,and promote the sustainable development of telemedicine.Meth-od/Process Taking comments from Haodf.com as an example,the paper first uses bidirectional encoder representations from transformers(BERT)to generate word embeddings,which are then fed into a convolutional neural network(CNN)and a bidirectional long short-term memory(BiLSTM)network in a dual-channel manner.Finally,a feature fusion strategy is employed to obtain textual sentiment informa-tion to achieve a binary classification task.Result/Conclusion The proposed dual-channel model based on BERT can better integrate the advantages of CNN and BiLSTM.It achieves the highest classification accuracy and macro F1-score compared to other 9 models,including BERT,BERT_BiLSTM,BERT_CNN,etc.,which is effective in sentiment classification tasks for online medical reviews.
bidirectional encoder representations from transformers(BERT)convolutional neural network(CNN)bidirectional long short-term memory(BiLSTM)online medical reviewssentiment classificationdual-channel model
万方数据
维普
