Please use this identifier to cite or link to this item:
Title: Summarizing online customer reviews automatically based on topical structure
Authors: Zhan, J
Loh, HT
Liu, Y 
Keywords: Customer reviews
Multi-document summarization
Topical structure
Web mining
Issue Date: 2008
Publisher: Springer
Source: Lecture notes in business information processing, 2008, v. 8, no. 4, p. 245-256 How to cite?
Journal: Lecture notes in business information processing 
Abstract: Online customer reviews offer valuable information for merchants and potential shoppers in e-Commerce and e-Business. However, even for a single product, the number of reviews often amounts to hundreds or thousands. Thus, summarization of multiple customer reviews is helpful to extract the important issues that merchants and customers are concerned with. Existing methods of multi-document summarization divide documents into non-overlapping clusters first and then summarize each cluster of documents individually with the assumption that each cluster discusses a single topic. When applied to summarize customer reviews, it is however difficult to determine the number of clusters a priori without the domain knowledge, and moreover, topics often overlap with each other in a collection of customer reviews. This paper proposes a summarization approach based on the topical structure of multiple customer reviews. Instead of clustering and summarization, our approach extracts topics from a collection of reviews and further ranks the topics based on their frequency. The summary is then generated according to the ranked topics. The evaluation results showed that our approach outperformed the baseline summarization systems, i.e. Copernic summarizer and clustering-summarization, in terms of users' responsiveness.
Description: Third International Conference on Web information systems and technologies, WEBIST 2007, Barcelona, Spain, March 3-6, 2007
ISSN: 1865-1348
EISSN: 1865-1356
Appears in Collections:Conference Paper

View full-text via PolyU eLinks SFX Query
Show full item record

Page view(s)

Citations as of Dec 16, 2018

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.