Mining Product Features from Free-Text Customer Reviews: An SVM-Based Approach

Author

Yu, Chuanming

Author_Institution

Dept. of Syst. Anal. & Inf. Manage., Univ. of Shanghai for Sci. & Technol., Shanghai, China

fYear

2009

fDate

26-28 Dec. 2009

Firstpage

900

Lastpage

903

Abstract

This study examines how the Support Vector Machine (SVM) combined with natural language processing techniques can be used to identify product features from free-text customer reviews. To verify the validity of the proposed approach, 22,157 restaurant reviews are collected and 3,701 sentences are randomly selected and manually annotated. The experiment results show that the average precision and recall are both higher than those of the Maximum Entropy (ME) based approach.

Keywords

data mining; identification technology; maximum entropy methods; natural language processing; support vector machines; SVM-based approach; free-text customer reviews; maximum entropy based approach; natural language processing technique; product feature identification; product feature mining; support vector machine; Constraint optimization; Humans; Information analysis; Information management; Information science; Internet; Kernel; Natural language processing; Support vector machine classification; Support vector machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Information Science and Engineering (ICISE), 2009 1st International Conference on

Conference_Location

Nanjing

Print_ISBN

978-1-4244-4909-5

Type

conf

DOI

10.1109/ICISE.2009.743

Filename

5454669