Prioritising engineering characteristics based on customer online reviews for quality function deployment

In market-driven product design, customer requirements (CRs) are usually obtained from consumer surveys. However, valuable CRs can also be found in a large number of online reviews. Largely due to their free text nature and the quantity, these reviews are often neglected and are seldom utilised directly by designers. In this work, one important question in quality function deployment on how to prioritise engineering characteristics (ECs) is investigated. Customer opinions concerning ECs are extracted from online reviews. By taking advantage of such opinion information, an ordinal classification approach is proposed to prioritise ECs. In a pairwise manner, in which customer opinions are deemed as features and the overall customer satisfactions are regarded as the target values, the weights of ECs are derived. Furthermore, an integer linear programming model is implemented to convert the pairwise results into the original customer satisfaction ratings. Finally, an exploratory case study is presented using reviews of four branded printers collected from Amazon and their analysis was conducted by two experienced design engineers. The experimental study reveals the merits of the proposed approach.

[1]  Juite Wang,et al.  Fuzzy outranking approach to prioritize design requirements in quality function deployment , 1999 .

[2]  Eduard Hovy,et al.  Identifying Opinion Holders for Question Answering in Opinion Texts , 2005 .

[3]  Han Tong Loh,et al.  Gather customer concerns from online product reviews - A text summarization approach , 2009, Expert Syst. Appl..

[4]  Han Tong Loh,et al.  Knowledge Discovery and Management for Product Design through Text Mining - a Case Study of Online Information Integration for Designers , 2007 .

[5]  Thore Graepel,et al.  Large Margin Rank Boundaries for Ordinal Regression , 2000 .

[6]  Franco Scarselli,et al.  SortNet: Learning to Rank by a Neural Preference Function , 2011, IEEE Transactions on Neural Networks.

[7]  Yoram Singer,et al.  An Efficient Boosting Algorithm for Combining Preferences by , 2013 .

[8]  Tie-Yan Liu,et al.  Learning to rank for information retrieval (LR4IR 2007) , 2007, SIGF.

[9]  Dragomir R. Radev,et al.  Identifying Text Polarity Using Random Walks , 2010, ACL.

[10]  Lyle Ungar,et al.  Discovery of significant emerging trends , 2010, KDD.

[11]  Gregory N. Hullender,et al.  Learning to rank using gradient descent , 2005, ICML.

[12]  P. K. Kannan,et al.  Customer-Driven Product Design Selection Using Web Based User-Generated Content , 2011, DAC 2011.

[13]  Qisheng Gao,et al.  A grey method of prioritizing engineering characteristics in QFD , 2009, 2009 Chinese Control and Decision Conference.

[14]  Kit Yan Chan,et al.  Modelling customer satisfaction for product development using genetic programming , 2011 .

[15]  Tao Qin,et al.  Ranking with multiple hyperplanes , 2007, SIGIR.

[16]  Kwai-Sang Chin,et al.  Technical importance ratings in fuzzy QFD by integrating fuzzy normalization and fuzzy weighted average , 2011, Comput. Math. Appl..

[17]  Zeynep Sener,et al.  A combined fuzzy linear regression and fuzzy multiple objective programming approach for setting target levels in quality function deployment , 2011, Expert Syst. Appl..

[18]  King Lun Choy,et al.  A novel fuzzy group decision-making approach to prioritising engineering characteristics in QFD under uncertainties , 2011 .

[19]  Tie-Yan Liu,et al.  Directly optimizing evaluation measures in learning to rank , 2008, SIGIR.

[20]  Zaifang Zhang,et al.  An integrated approach for rating engineering characteristics' final importance in product-service system development , 2010, Comput. Ind. Eng..

[21]  Wei Zhang,et al.  Improve the effectiveness of the opinion retrieval and opinion polarity classification , 2008, CIKM '08.

[22]  Yulan He,et al.  Joint sentiment/topic model for sentiment analysis , 2009, CIKM.

[23]  Richard Y. K. Fung,et al.  Identifying helpful online reviews: A product designer's perspective , 2013, Comput. Aided Des..

[24]  M. Trusov,et al.  Estimating Aggregate Consumer Preferences from Online Product Reviews , 2010 .

[25]  John Carroll,et al.  Automatic Seed Word Selection for Unsupervised Sentiment Classification of Chinese Text , 2008, COLING.

[26]  Gülçin Büyüközkan,et al.  A fuzzy optimization model for QFD planning process using analytic network approach , 2006, Eur. J. Oper. Res..

[27]  Conrad S. Tucker,et al.  Predicting emerging product design trend by mining publicly available customer review data , 2011 .

[28]  Bing Liu,et al.  Mining and summarizing customer reviews , 2004, KDD.

[29]  Thorsten Joachims,et al.  Optimizing search engines using clickthrough data , 2002, KDD.

[30]  Ming-Lu Wu,et al.  A systematic approach to quality function deployment with a full illustrative example , 2005 .

[31]  Kit Yan Chan,et al.  A methodology of generating customer satisfaction models for new product development using a neuro-fuzzy approach , 2009, Expert Syst. Appl..

[32]  Jiafu Tang,et al.  Rating technical attributes in fuzzy QFD by integrating fuzzy weighted average method and fuzzy expected value operator , 2006, Eur. J. Oper. Res..

[33]  Kam-Fai Wong,et al.  A Unified Graph Model for Sentence-Based Opinion Retrieval , 2010, ACL.

[34]  Kit Yan Chan,et al.  A generalised fuzzy least-squares regression approach to modelling relationships in QFD , 2010 .

[35]  Rajeev Jain,et al.  Integration of Kano’s Model into quality function deployment (QFD) , 2011 .

[36]  Tie-Yan Liu,et al.  Learning to rank for information retrieval , 2009, SIGIR.

[37]  Bing Liu,et al.  Opinion observer: analyzing and comparing opinions on the Web , 2005, WWW '05.