中文长短期记忆网络的情感分析  

Emotional Analysis of Chinese Long Short-term Memory Network

作　　者：郑永奇 ZHENG Yongqi(Zhengzhou Shuqing Medical College,Zhengzhou 450064,China)

机构地区：[1]郑州澍青医学高等专科学校,郑州450064

出　　处：《移动信息》2023年第7期211-212,216,共3页MOBILE INFORMATION

摘　　要：文中探讨了循环神经网络(RNN)在文本情感分析中的应用,并提出了一种新的混合模型一一LSTM-CNN文本情感分析模型,它融合了长短时记忆网络(LSTM)和卷积神经网络(CNN)的优势,可以更好地处理文本数据中的上下文信息和局部特征。为了验证模型的有效性,文中使用开源爬虫工具抓取了《流浪地球2》的豆瓣评论构建数据集,然后对所提模型进行了训练和测试。结果表明,当词向量维度为100时,模型的性能达到最优,此时的精确率、召回率、F1值和准确率分别为84.2%,88.6%,86.2%和90.0%,证实了该模型在文本情感分类任务上的优越性。This paper discusses the application of recurrent neural networks(RNN)in text sentiment analysis,and proposes a new hybrid model,the LSTM-CNN text sentiment analysis model,which combines the advantages of long and short-term memory networks(LSTM)and convolutional neural networks(CNN),which can better handle contextual information and local features in text data.In order to verify the validity of the model,the open source crawler tool is used to grab the watercress review of“The Wandering Earth 2”to build a dataset,and then the proposed model is trained and tested.The results show that the performance of the model is optimal when the word vector dimension is 1oo,and the accuracy rate,recall rate,F1 value and accuracy rate at this time are 84.2%,88.6%,86.2%and 90.0%,respectively,confirming the model Superiority in text sentiment classification tasks.

关 键 词：长短期记忆网络 卷积神经网络 情感分析 中文文本 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]