Mathematics and Computer Science Department, Faculty of Science, Beni-Suef University, Beni Suef 62511, Egypt.
Information & Computing Lab, AtlanTTIC Research Center, Telecommunication Engineering School, Universidade de Vigo, 36310 Vigo, Spain.
Sensors (Basel). 2021 Jan 18;21(2):636. doi: 10.3390/s21020636.
Recently, it has been found that e-commerce (EC) websites provide a large amount of useful information that exceed the human cognitive processing capacity. In order to help customers in comparing alternatives when buying a product, previous research authors have designed opinion summarization systems based on customer reviews. They ignored the template information provided by manufacturers, although its descriptive information has the most useful product characteristics and texts are linguistically correct, unlike reviews. Therefore, this paper proposes a methodology coined as SEOpinion (summarization and exploration of opinions) to summarize aspects and spot opinion(s) regarding them using a combination of template information with customer reviews in two main phases. First, the hierarchical aspect extraction (HAE) phase creates a hierarchy of aspects from the template. Subsequently, the hierarchical aspect-based opinion summarization (HAOS) phase enriches this hierarchy with customers' opinions to be shown to other potential buyers. To test the feasibility of using deep learning-based BERT techniques with our approach, we created a corpus by gathering information from the top five EC websites for laptops. The experimental results showed that recurrent neural network (RNN) achieved better results (77.4% and 82.6% in terms of F1-measure for the first and second phases, respectively) than the convolutional neural network (CNN) and the support vector machine (SVM) technique.
最近，人们发现电子商务 (EC) 网站提供了大量超出人类认知处理能力的有用信息。为了帮助客户在购买产品时比较选择，之前的研究作者已经设计了基于客户评论的观点总结系统。他们忽略了制造商提供的模板信息，尽管其描述性信息具有最有用的产品特征，并且文本在语法上是正确的，不像评论那样。因此，本文提出了一种名为 SEOpinion（观点总结和探索）的方法，该方法结合客户评论和模板信息，在两个主要阶段中使用组合来总结方面并发现有关方面的观点。首先，层次方面提取 (HAE) 阶段从模板中创建方面层次结构。随后，基于层次方面的观点总结 (HAOS) 阶段使用客户的意见丰富这个层次结构，以便展示给其他潜在买家。为了测试使用基于深度学习的 BERT 技术与我们的方法的可行性，我们通过从五大笔记本电脑 EC 网站收集信息创建了一个语料库。实验结果表明，递归神经网络 (RNN) 在第一阶段和第二阶段的 F1 测度方面（分别为 77.4%和 82.6%）的表现优于卷积神经网络 (CNN) 和支持向量机 (SVM) 技术。
