Summarising customer online reviews using a new text mining approach

Neda AleEbrahim and Mohammad Fathian

International Journal of Business Information Systems, 2013, vol. 13, issue 3, 343-358

Abstract: In recent years, with the expansion of electronic commerce, the number of customer online reviews available on the internet is growing rapidly. Lots of online merchant's websites ask the customers to leave a review about their experiences with the products. The reviews gathered from these websites are rich source of information for product development and marketing. The large volume of reviews that a product receives, make it hard for a potential customer or a manufacturer to read them and know about the customers' preferences, needs and experiences. So, this large volume of text data needs to be summarised using text mining approaches. The approach used in this paper to overcome this problem, is to develop a text summarisation system which extracts and groups the representative sentences of customer reviews. The proposed system, first extracts key topics discussed frequently in the customer review texts in the form of sequences of words. Then, the proposed system, groups the sentences assigned to the key topics, based on their semantic and syntactic similarity, using a genetic clustering algorithm. The evaluation result of the proposed system shows that the technique is effective and outperforms an existing text summarisation method.

Keywords: customer online reviews; text summarisation; text mining; frequent words; word sequences; syntactic similarity; semantic similarity; genetic algorithms; clustering algorithms; electronic commerce; e-commerce; product reviews; product development; marketing; key topics. (search for similar items in EconPapers)
Date: 2013
References: Add references at CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://www.inderscience.com/link.php?id=54468 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ids:ijbisy:v:13:y:2013:i:3:p:343-358

Access Statistics for this article

More articles in International Journal of Business Information Systems from Inderscience Enterprises Ltd
Bibliographic data for series maintained by Sarah Parker ().