Opinion mining for Thai restaurant reviews using neural networks and mRMR feature selection

Author

Claypo, Niphat ; Jaiyen, Saichon

Author_Institution

Dept. of Comput. Sci., King Mongkut´s Inst. of Technol. Ladkrabang, Bangkok, Thailand

fYear

2014

fDate

July 30 2014-Aug. 1 2014

Firstpage

394

Lastpage

397

Abstract

Currently, Thai restaurants are popular around the world. There are tons of reviews related to foods and services in social networking websites. These tons of customer reviews make it difficult to analyze the opinions of customer toward foods and services. To help the businesses, the model of opinion mining is proposed for classifying the reviews and to analyze the attitude of customers for improving their products and services. In this research, the artificial neural network is applied to classify the positive and negative reviews. In addition, the mRMR feature selection is used to select the features of data in order to reduce the number of features in the data set. Consequently, the computational times of learning algorithms for neural networks are reduced. The experimental results show that the neural network is an effective model for classifying the Thai restaurant reviews.

Keywords

catering industry; data mining; feature selection; learning (artificial intelligence); natural language processing; neural nets; pattern classification; social networking (online); Thai restaurant reviews; artificial neural network; computational times; customer review classification; learning algorithms; mRMR feature selection; opinion mining model; social networking Web sites; Accuracy; Artificial neural networks; Data mining; Support vector machines; Testing; Training; Classification; Feature selection; Support Vector Machine (SVM); minimal-redundancy-maximal-relevance (mRMR); multilayer perceptron (MLP); radial basis function (RBF);

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Science and Engineering Conference (ICSEC), 2014 International

Conference_Location

Khon Kaen

Print_ISBN

978-1-4799-4965-6

Type

conf

DOI

10.1109/ICSEC.2014.6978229

Filename

6978229