Product-oriented review summarization and scoring  

作　　者：Rong ZHANG Wenzhe YU Chaofeng SHA Xiaofeng HE Aoying ZHOU 

机构地区：[1]Institute of Data Science and Engineering, Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai 200062, China [2]School of Computer Science, Fudan University, Shanghai 200433, China

出　　处：《Frontiers of Computer Science》2015年第2期210-223,共14页中国计算机科学前沿（英文版）

基　　金：This work was partially supported by the National Science Foundation of China （Grant Nos. 61103039, 61232002, 61472345）, National Basic Research Program of China （2010CB731402） and Wuhan Key Lab Research Foundation （SKLSE2012-09-16）.

摘　　要：Currently, mere are many onune review weo sites where consumers can freely write comments about different kinds of products and services. These comments are quite useful for other potential consumers. However, the number of online comments is often large and the number continues to grow as more and more consumers contribute. In addition, one comment may mention more than one product and con- tain opinions about different products, mentioning something good and something bad. However, they share only a single overall score, Therefore, it is not easy to know the quality of an individual product from these comments. This paper presents a novel approach to generate review summaries including scores and description snippets with re- spect to each individual product. From the large number of comments, we first extract the context （snippet） that includes a description of the products and choose those snippets that express consumer opinions on them. We then propose several methods to predict the rating （from 1 to 5 stars） of the snip- pets. Finally, we derive a generic framework for generating summaries from the snippets. We design a new snippet selec- tion algorithm to ensure that the returned results preserve the opinion-aspect statistical properties and attribute-aspect cov- erage based on a standard seat allocation algorithm. Through experiments we demonstrate empirically that our methods are effective. We also quantitatively evaluate each step of our ap- proach.Currently, mere are many onune review weo sites where consumers can freely write comments about different kinds of products and services. These comments are quite useful for other potential consumers. However, the number of online comments is often large and the number continues to grow as more and more consumers contribute. In addition, one comment may mention more than one product and con- tain opinions about different products, mentioning something good and something bad. However, they share only a single overall score, Therefore, it is not easy to know the quality of an individual product from these comments. This paper presents a novel approach to generate review summaries including scores and description snippets with re- spect to each individual product. From the large number of comments, we first extract the context （snippet） that includes a description of the products and choose those snippets that express consumer opinions on them. We then propose several methods to predict the rating （from 1 to 5 stars） of the snip- pets. Finally, we derive a generic framework for generating summaries from the snippets. We design a new snippet selec- tion algorithm to ensure that the returned results preserve the opinion-aspect statistical properties and attribute-aspect cov- erage based on a standard seat allocation algorithm. Through experiments we demonstrate empirically that our methods are effective. We also quantitatively evaluate each step of our ap- proach.

关 键 词：online transaction DIVERSIFICATION review sum-marization review scoring 

分 类 号：TP311.5[自动化与计算机技术—计算机软件与理论] TN929.533[自动化与计算机技术—计算机科学与技术]