Opinion Mining and Summarization of Hotel Reviews

Author

Raut, Vijay B. ; Londhe, D.D.

Author_Institution

Dept. of Inf. Technol., Pune Inst. of Comput. Technol., Pune, India

fYear

2014

Firstpage

556

Lastpage

559

Abstract

Everyday many users purchases product, book travel tickets, buy goods and services through web. Users also share their views about product, hotel, news, and topic on web in the form of reviews, blogs, comments etc. Many users read review information given on web to take decisions such as buying products, watching movie, going to restaurant etc. Reviews contain user´s opinion about product, event or topic. It is difficult for web users to read and understand contents from large number of reviews. Important and useful information can be extracted from reviews through opinion mining and summarization process. We presented machine learning and Senti Word Net based method for opinion mining from hotel reviews and sentence relevance score based method for opinion summarization of hotel reviews. We obtained about 87% of accuracy of hotel review classification as positive or negative review by machine learning method. The classified and summarized hotel review information helps web users to understand review contents easily in a short time.

Keywords

Web sites; consumer behaviour; data mining; hotel industry; learning (artificial intelligence); natural language processing; pattern classification; text analysis; SentiWordNet based method; Web users user opinion machine learning; blogs; hotel review classification; hotel reviews summarization; opinion mining; opinion summarization; review contents; review information; sentence relevance score based method; travel tickets; Accuracy; Classification algorithms; Data mining; Information technology; Machine learning algorithms; Motion pictures; Sentiment analysis; Opinion Mining; Opinion Summarization; Text Mining;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Intelligence and Communication Networks (CICN), 2014 International Conference on

Print_ISBN

978-1-4799-6928-9

Type

conf

DOI

10.1109/CICN.2014.126

Filename

7065546