Please wait a minute...
Applied Mathematics-A Journal of Chinese Universities  2019, Vol. 34 Issue (3): 356-378    DOI: 10.1007/s11766-019-3698-x
    
Generating Quantitative Product Profile Using Char-Word CNNs
XU Hai-rui ZHANG Wei-cheng LI Ming QIN Fei-wei
Department of State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou 310027, China.
 School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou 310027, China.
Generating Quantitative Product Profile Using Char-Word CNNs
XU Hai-rui ZHANG Wei-cheng LI Ming QIN Fei-wei
Department of State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou 310027, China.
 School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou 310027, China.
 全文: PDF 
摘要： The online customer reviews provide important information for product improvement and redesign. However, many reviews are redundant with only several short sentences, which may even conflict with each other on the same aspect of a product. Thus it is usually a very challenging task to extract useful design information from the reviews and provide a clear description on the product’s various aspects amongst its competitors. In order to resolve this issue, we propose an approach to build hierarchical product profiles to describe a product’s kernel design aspects quantitatively. It is achieved via three main strategies: a double propagation strategy to achieve the associated features and customers’ descriptions; a deep text processing network to build the aspect hierarchy; an aspect ranking approach to quantify each kernel design aspect. Experimental results validate the effectiveness of the proposed approach on online reviews. 
关键词： customer reviews;  quantitative product profile;  product aspect ranking;  deep learning    
Abstract: The online customer reviews provide important information for product improvement and redesign. However, many reviews are redundant with only several short sentences, which may even conflict with each other on the same aspect of a product. Thus it is usually a very challenging task to extract useful design information from the reviews and provide a clear description on the product’s various aspects amongst its competitors. In order to resolve this issue, we propose an approach to build hierarchical product profiles to describe a product’s kernel design aspects quantitatively. It is achieved via three main strategies: a double propagation strategy to achieve the associated features and customers’ descriptions; a deep text processing network to build the aspect hierarchy; an aspect ranking approach to quantify each kernel design aspect. Experimental results validate the effectiveness of the proposed approach on online reviews. 
Key words: customer reviews    quantitative product profile    product aspect ranking    deep learning
出版日期: 2019-09-20
CLC:  35B35  
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　
XU Hai-rui ZHANG Wei-cheng LI Ming QIN Fei-wei

引用本文:

XU Hai-rui ZHANG Wei-cheng LI Ming QIN Fei-wei. Generating Quantitative Product Profile Using Char-Word CNNs[J]. Applied Mathematics-A Journal of Chinese Universities, 2019, 34(3): 356-378.

XU Hai-rui ZHANG Wei-cheng LI Ming QIN Fei-wei. Generating Quantitative Product Profile Using Char-Word CNNs. Applied Mathematics-A Journal of Chinese Universities, 2019, 34(3): 356-378.

链接本文:

http://www.zjujournals.com/amjcub/CN/10.1007/s11766-019-3698-x    或    http://www.zjujournals.com/amjcub/CN/Y2019/V34/I3/356

[1] LI Shu-hua LIU Xiu-ping CAO Jun-jie WANG Shi-yao. Organic skeleton correspondence using part arrangements[J]. Applied Mathematics-A Journal of Chinese Universities, 2019, 34(3): 326-339.
[2] J Dhivya, B Sridevi. A novel similarity measure between intuitionistic fuzzy sets based on the mid points of transformed triangular fuzzy numbers with applications to pattern recognition and medical diagnosis[J]. Applied Mathematics-A Journal of Chinese Universities, 2019, 34(2): 229-252.
[3] SHIM Eungjune, KIM Youngjun, LEE Deukhee, LEE Byung Hoon, WOO Sungkyung, LEE Kunwoo. 2D-3D registration for 3D analysis of lower limb alignment in a weight-bearing condition[J]. Applied Mathematics-A Journal of Chinese Universities, 2018, 33(1): 59-70.