alphanumeric journal
The Journal of Operations Research, Statistics, Econometrics and Management Information Systems
Text Mining as a Supporting Process for VoC Clarification
bib
Abstract
In product development, the foremost issue is to identify "what" the customers’ expectations would be from the product. As a promising approach to the product development, Quality Function Deployment also gives crucial importance to the collection and analysis of Voice of the Customer (VoC) to deduce true customer needs. Data sources of VoC include surveys, interviews, focus groups, gemba visits as well as customer reviews which can be collected through call centers, internet homepages, blogs, and microblogs in social networks. Customers’ verbatim or reviews obtained from these resources require more detailed extraction to define them as the positive restatement of problems, opportunities or image issues independent of the product or the solution. Basically, this clarification process is a content analysis in which the developers usually seek to extract and classify the spoken-unspoken customer needs from VoC. This labor-intensive manual approach brings subjectivity to the analysis and can take so much time in the case of having condensed and large-volume text data. During the past decade, the field of text mining has enabled to solve these kinds of problems efficiently by unlocking hidden information and developing new knowledge; exploring new horizons; and improving the research process and quality. This paper utilizes a particular algorithm of text clustering, a recently popular field of interest in text mining, to analyze VoC and shows how text mining can also support the clarification process for better extraction of customer needs. Practical implications are presented through analysis of online customer reviews for a product.
Keywords: Quality Function Deployment (QFD), Text Clustering, Text Mining, Voice of the Customer (VoC)
Jel Classification: C38, C55, C88, M11, M15, M31
Müşteri Sesinin Ayrıştırılmasını Destekleyen Bir Süreç Olarak Metin Madenciliği
Öz
Ürün geliştirmede en başta gelen konu, müşterilerin üründen beklentilerinin ne olacağını belirlemektir. Ürün geliştirme için gelecek vaadeden bir yaklaşım olarak, Kalite Fonksiyon Göçerimi de, gerçek müşteri ihtiyaçlarını ortaya çıkarmak için Müşteri Sesinin toplanmasına ve analizine oldukça önem vermektedir. Müşteri Sesinin veri kaynaklarını anketler, mülakatlar, odak grupları, gemba ziyaretlerinin yanı sıra çağrı merkezlerinden, internet sayfalarından, web günlüklerinden (blog) ve sosyal ağlardaki mikro web günlüklerinden toplanabilen müşteri yorumları oluşturmaktadır. Bu kaynaklardan elde edilen müşteri ifadeleri veya yorumlarının, ürün ya da çözümden bağımsız problem, fırsat veya imaja yönelik konular bazında yeniden olumlu ifadeler şeklinde tanımlamak için daha detaylı ayrıştırılması gerekmektedir. Temel olarak, bu ayrıştırma süreci, geliştiricilerin genellikle müşteri sesinden dile getirilen ve getirilmeyen müşteri ihtiyaçlarını çıkarmaya ve sınıflandırmaya çalıştıkları bir içerik analizidir. Bu emek-yoğun manuel yaklaşım, analize öznellik getirmekte ve yoğun ve büyük hacimde metin verilerin varlığı durumunda çok fazla zaman alabilmektedir. Son on yılda, metin madenciliği alanı gizli bilgileri açığa çıkararak ve yeni bilgi geliştirerek, yeni ufuklar keşfederek, araştırma sürecini ve kalitesini iyileştirerek bu tür problemlerin etkin bir şekilde çözümüne olanak sağlamaktadır. Bu çalışma, müşteri sesini analiz etmek için, metin madenciliğinin son yıllarda popüler ilgi alanı haline gelen metin sınıflandırmaya yönelik özel bir algoritma kullanmakta ve “gerçek” müşteri ihtiyaçlarını daha doğru bir şekilde belirlemek için metin madenciliğinin ayrıştırma sürecini nasıl destekleyebileceğini göstermektedir. Uygulama açısından etkileri, bir ürüne ilişkin online müşteri yorumlarının analiziyle sunulmaktadır.
Anahtar Kelimeler: Kalite Fonksiyon Göçerimi, Metin Madenciliği, Metin Sınıflandırma, Müşteri Sesi
Suggested citation
(). Text Mining as a Supporting Process for VoC Clarification. Alphanumeric Journal, 3(1), 25-40. http://dx.doi.org/10.17093/aj.2015.3.1.5000105108
References
- Aggarwal, C.C., Zhai, C.X.(Eds), (2012). Mining Text Data,Springer, New York, e-ISBN 978-1-4614-3223-4.
- Chandrasekhar, T., Thangavel, K., Elayaraja,E.,(2011). Performance analysis of enhanced clustering algorithm for gene expression data, International Journal of Computer Science Issues, 8(6-3), 253-257.
- Cutting, D.R., Pedersen, J.O., Karger, D.R., Tukey, J.W., (1992). Scatter/Gather: A cluster-based approach to browsing large document collections. SIGIR '92: Proceedings of the 15th annual international ACM SIGIR conference on Research and development in information retrieval, New York, NY, USA,ACM Press, 318-329.
- Feldman, R., Dagan, I., (1995). KDT-Knowledge Discovery in Texts. Proceedings of the First International Conference on Knowledge Discovery, 112-117.
- Gamon, M., Aue, A., Oliver S.C., Ringger, E.,(2005). Pulse: Mining customer opinions from free text, Advances in Intelligent Data Analysis VI, 6th International Symposium on Intelligent Data Analysis, IDA, Proceedings, Madrid, Spain, September 8-10, Springer (Lecture Notes in Computer Science), 121-132.
- Gupta, V., Lehal, G.S., (2009). A survey of text mining techniques and algorithms, Journal of Emerging Technologies in Web Intelligence, 1 (1), 60-76.
- Han, J., Kamber, M., Pei, J., (2012). Data Mining, Concepts and Techniques, Morgan Kaufmann Publishers, Waltham, MA, USA.
- Harvard TagTeam, (2013). http://tagteam.harvard.edu/hub_feeds/1981/feed_items/274117. Access: 01.08.2014
- Hotto, A., Nirnberger, A., Paaβ, G., Augustin, S., (2005). A Brief Survey of Text Mining. http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.210.158&rep=rep1&type=pdf. Access date: 05.05.2014, pp.4-5.
- Jain, A.K., Dubes, R.C., (1998). Algorithms for Clustering Data, PrenticeHall, Englewood Cliffs, NJ.
- Kroeze, J.H., Matthee, M.C., Bothma, T.J.D., (2004). Differentiating between data-mining and text-mining terminology. South African Journal of Information Management, 6(4),
- Kwale, F.M., (2013). A critical review of k means text clustering algorithms. International Journal of Advanced Research in Computer Science, 4(9), 1-9.
- Mooney, R.J., Bunescu, R., (2005). Mining Knowledge fromText Using Information Extraction, SIGKDD Explorations, 7(1),3-10.
- Steinbach, M., Karypis, G., Kumar, V.,(2000). A Comparison of Document Clustering Techniques. KDD Workshop on text mining.
- Turi, R.H., Ray, S.,(2000). Determination of the Number of Clusters in Colour Image Segmentation, SCSSE Monash University, Clayton Vic Australia.
- Witten, I.H., (2004). Adaptive text mining: inferring structure from sequences, Journal of Discrete Algorithms, 2, 137–159.
- Wordle, (2013). http://www.wordle.net/. Access date: 05/01/2015.
- Zhao, Y., Karypis, G., (2004). Empirical and theoretical comparisons of selected criterion functions for document clustering, Machine Learning, 55(3),311–331.
2015.03.01.MIS.01
alphanumeric journal
Pages 25-40
Received: March 18, 2015
Accepted: May 16, 2015
Published: June 30, 2015
2015 Kapucugil İkiz, A., Özdağoğlu, G.
This is an Open Access article, distributed under the terms of the Creative Commons Attribution licence, which permits unrestricted re-use, distribution, and reproduction in any medium, provided the original work is properly cited.
scan QR code to access this article from your mobile device
Contact Us
Faculty of Transportation and Logistics, Istanbul University
Beyazit Campus 34452 Fatih/Istanbul/TURKEY
Bahadır Fatih Yıldırım, Ph.D.
editor@alphanumericjournal.com
+ 90 (212) 440 00 00 - 13219
alphanumeric journal
alphanumeric journal has been publishing as "International Peer-Reviewed Journal" every six months since 2013. alphanumeric serves as a vehicle for researchers and practitioners in the field of quantitative methods, and is enabling a process of sharing in all fields related to the operations research, statistics, econometrics and management informations systems in order to enhance the quality on a globe scale.