引用本文
  • 胡晓丽,张于贤,黄思睿.融合ChineseBERT和双向注意力流的中文商品评论方面情感分析[J].广西科学,2023,30(1):187-195.    [点击复制]
  • HU Xiaoli,ZHANG Yuxian,HUANG Sirui.Aspect Sentiment Analysis for Chinese Commodity Reviews Based on ChineseBERT and Bidirectional Attention Flow[J].Guangxi Sciences,2023,30(1):187-195.   [点击复制]
【打印本页】 【在线阅读全文】【下载PDF全文】 查看/发表评论下载PDF阅读器关闭

←前一篇|后一篇→

过刊浏览    高级检索

本文已被:浏览 137次   下载 459 本文二维码信息
码上扫一扫!
融合ChineseBERT和双向注意力流的中文商品评论方面情感分析
胡晓丽1, 张于贤2, 黄思睿3
0
(1.桂林电子科技大学计算机与信息安全学院, 广西桂林 541004;2.桂林电子科技大学商学院, 广西桂林 541004;3.桂林电子科技大学, 广西可信软件重点实验室, 广西桂林 541004)
摘要:
准确分类电商平台中用户评论所包含的多个方面的情感极性,能够提升购买决策的有效性。为此,提出一种融合ChineseBERT和双向注意力流(Bidirectional Attention Flow,BiDAF)的中文商品评论方面情感分析模型。首先,通过融合拼音与字形的ChineseBERT预训练语言模型获得评论文本和方面文本的词嵌入,并采用从位置编码和内存压缩注意力两个方面改进的Transformer来表征评论文本和方面文本的语义信息。然后,使用双向注意力流学习评论文本与方面文本的关系,找出评论文本和方面文本中关键信息所对应的词语。最后,将Transformer和双向注意力流的输出同时输入到多层感知机(Multilayer Perceptron,MLP)中,进行信息级联和情感极性的分类输出。测试结果表明,提出的模型在两个数据集上的准确率分别为82.90%和71.08%,F1分数分别为82.81%和70.98%。
关键词:  商品评论|方面情感分析|词嵌入模型|注意力机制|双向注意力流
DOI:10.13656/j.cnki.gxkx.20230308.020
基金项目:国家自然科学基金项目(62267003,61967005,U18112645)和桂林市科学研究与技术开发计划项目(2020011123)资助。
Aspect Sentiment Analysis for Chinese Commodity Reviews Based on ChineseBERT and Bidirectional Attention Flow
HU Xiaoli1, ZHANG Yuxian2, HUANG Sirui3
(1.School of Computer Science and Information Security, Guilin University of Electronic Technology, Guilin, Guangxi, 541004, China;2.Business School, Guilin University of Electronic Technology, Guilin, Guangxi, 541004, China;3.Guangxi Key Laboratory of Trusted Software, Guilin University of Electronic Technology, Guilin, Guangxi, 541004, China)
Abstract:
Accurately classifying the sentiment polarity of various aspects contained in user reviews in E-commerce platforms can improve the effectiveness of purchase decisions.Therefore,a sentiment analysis model of Chinese product reviews based on ChineseBERT and Bidirectional Attention Flow (BiDAF) is proposed.Firstly,the word embedding of the review text and the aspect text is obtained by the ChineseBERT pre-trained language model that integrates pinyin and glyph,and the semantic information of the review text and the aspect text is represented by the Transformer improved from two aspects of position coding and memory compression attention.Then,the bidirectional attention flow is used to learn the relationship between the review text and the aspect text,and find out the words corresponding to the key information in the review text and the aspect text.Finally,the outputs of Transformer and bidirectional attention flow are simultaneously input into Multilayer Perception (MLP) for information cascade and sentiment polarity classification output.The test results show that the accuracy of the proposed model on the two data sets is 82.90% and 71.08%,respectively,and the F1 scores are 82.81% and 70.98% respectively.
Key words:  product reviews|aspect sentiment analysis|word embedding model|attention mechanism|bidirectional attention flow

用微信扫一扫

用微信扫一扫