0
research-article

A methodology for predicting future importance of customer needs based on online customer reviews

[+] Author and Article Information
Huimin Jiang

Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Hong Kong, PRC
huimin.jiang@connect.polyu.hk

C.K. Kwong

Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Hong Kong, PRC
c.k.kwong@polyu.edu.hk

K.L. Yung

Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Hong Kong, PRC
kl.yung@polyu.edu.hk

1Corresponding author.

ASME doi:10.1115/1.4037348 History: Received February 24, 2017; Revised July 06, 2017

Abstract

Previous studies conducted customer surveys based on questionnaires and interviews, and the survey data was then utilized to analyze product features. In recent years, online customer reviews on products became extremely popular, which contain rich information on customer opinions and expectations. However, previous studies failed to properly address the determination of the importance of product features and prediction of their future importance based on online reviews. Accordingly, a methodology for predicting future importance weights of product features based on online customer reviews is proposed in this paper which mainly involves opinion mining, a fuzzy inference method, and a fuzzy time series method. Opinion mining is adopted to analyze the online reviews and extract product features. A fuzzy inference method is used to determine the importance weights of product features using both frequencies and sentiment scores obtained from opinion mining. A fuzzy time series method is adopted to predict the future importance of product features. A case study on electric irons was conducted to illustrate the proposed methodology. To evaluate the effectiveness of the fuzzy time series method in predicting the future importance, the results obtained by the fuzzy time series method are compared with those obtained by the three common forecasting methods. The results of the comparison show that the prediction results based on fuzzy time series method are better than those based on exponential smoothing, simple moving average and fuzzy moving average method.

Copyright (c) 2017 by ASME
Topics: Mining , Time series
Your Session has timed out. Please sign back in to continue.

References

Figures

Tables

Errata

Discussions

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In