Title

推薦產品之相關性對購物經驗之影響

Translated Titles

Effects of Relevance of Recommended Products on Shopping Experience

Authors

黃琬琪

Key Words

相關性 ; 卡片分類 ; 科技接受模式 ; Relevance ; Card sorting ; Technology Acceptance Model

PublicationName

臺北科技大學工業工程與管理系碩士班學位論文

Volume or Term/Year and Month of Publication

2014年

Academic Degree Category

碩士

Advisor

梁曉帆

Content Language

繁體中文

Chinese Abstract

產品推薦是線上購物中常見的功能,推薦之相關產品通常在畫面中列於主要產品下方,但畫面上也有較不相關的廣告產品。由文獻已知消費者對相關性高的產品感受較佳,對較不相關的產品感受較差,進而影響了消費者的購買態度。因此,產品相關性與消費者感受之間的關係十分密切且重要,然而目前仍未有足夠的文獻探討兩者的關係。所以本研究主題為探討消費者的購物經驗如何隨著推薦產品相關程度的變化而改變。方法第一階段為確認產品間的相關程度,以20位受測者分類100項產品的結果建構出群集樹狀圖,再依據群集結構分成最高、高、中、低與最低等五階產品相關程度,即為本研究之自變數,第二階段再以此五階相關程度分別製作五種推薦產品畫面,每種畫面皆有一項主要產品和四項推薦產品,讓40位受測者在無時間限制下瀏覽這五種畫面,並以購物經驗問卷衡量他們瀏覽推薦產品時對於推薦資訊品質、購物攸關性及感知有用性的感受,即為本研究之應變數。本研究結果為,不論中到低相關或高到中相關的購物經驗降幅,都顯著大於最高到高相關以及低到最低相關之降幅。此趨勢應可以邏輯斯(logistic)方程式解釋,因此利用曲線估計模型得出產品相關性與購物經驗之迴歸方程式,此迴歸方程式可讓推薦系統設計者了解產品相關性與線上購物經驗之關係,將能有助於設計策略之訂定。

English Abstract

Recommended products are commonly displayed around target products on shopping websites. Most of the recommended products relate to the target products, but some advertised products may not be so relevant. Previous research has shown that the relevance of recommended products to target products affects customers’ shopping experience and attitude. The higher the relevance is, the more positive the experience and attitude will be. Therefore, the relationship between relevance of recommended products and shopping experience is important. However, insufficient research has been done to explore this relationship. The purpose of this paper is to investigate how customer’s shopping experience changes to recommended products according to different degrees of relevance to target products. To obtain the relevance of products, twenty participants were asked to sort 100 products so that a dendrogram about product relevance was constructed. Based on the dendrogram, 5 levels of relevance were identified. They were the highest relevance, high relevance, medium relevance, low relevance and the lowest relevance, and served as the 5 levels of the independent variable. Five shopping webpages were designed according to these 5 levels of relevance. For each webpage, a target product displayed on the center of the page and 4 recommended products horizontally listed below it. Another40 participants were asked to browse all the five webpages in a random order and to complete a shopping experience questionnaire for measuring participants’ shopping experience of recommendation information quality, shopping relevance and perceived usefulness. Results indicated that the declines of shopping experience from medium to low relevance and from high to medium relevance were significantly sharper than the declines from highest to high relevance and from low to the lowest relevance. A logistic function should be able to describe the relationship between the shopping experience and product relevance. Thus, through the curve estimation modeling, a logistic regression function was derived. It is expected that designers of recommendation systems can apply this function to their design decisions.

Topic Category 管理學院 > 工業工程與管理系碩士班
工程學 > 工程學總論
社會科學 > 管理學
Reference
  1. 1.呂昌鴻,探討運轉員對於龍門核電廠系統架構之心智模式,碩士論文,台北科技大學工業工程與管理系碩士班,台北,2009。
    連結:
  2. 2.T. Saracevic, "Relevance : A Review of and a Framework for the Thinking on the Notion in Information Science, "Journal of the American Society for Information Science, 1975, vol.26, no. 6 , pp. 321-343
    連結:
  3. 7.J. Choi, H.J.Lee,F.Sajjad, H. Lee, "The influence of national culture on the attitude towards mobile recommender systems", Technological Forecasting & Social Change , 2014, pp.65-79
    連結:
  4. 10.Y. Li, L. Lu,L.Xuefeng,"A hybrid collaborative filtering method for multiple-interests and multiple-content recommendation in E-Commerce, "Expert System With Applications, vol. 28 , no.1 , 2005, pp.67-77
    連結:
  5. 11.Y.H. Cho, J. K. Kim,"Application of Web usage mining and product taxonomy to collaborative recommendations in e-commerce, "Expert Systems with applications ,vol. 26 ,2004, pp. 233–246
    連結:
  6. 12.A. Albadvi, and M. Shahbazi, "A hybrid recommendation technique based on product category attributes, "Expert System with Application, 2009, vol.36, pp. 11480-11488
    連結:
  7. 13.B. Jeong, J. Lee, H. Cho, "Improving memory-based collaborative filtering via similarity updatingand prediction modulation, "Information Sciences, vol.180, no.5, 2010, pp. 602-612
    連結:
  8. 14.K. Choi, Y. Suh,"A new similarity function for selecting neighbors for each target item in collaborative filtering, "Knowledge-Based Systems,vol. 37 , 2013, pp. 146-153
    連結:
  9. 16.J. L. Herlocker, J.A. Konstan, L.G. Terveen and J.T. Riedl, " Evaluating Collaborative Filtering Recommender Systems, " ACM Transactions on Information Systems, vol.22, no. 1, 2004, pp. 5-53
    連結:
  10. 19.T. Tullis and L. Wood, "How many users are enough for a card-sorting study, " In Proceedings of the UPA, 2004
    連結:
  11. 20.S.F. Liang and L.T. Tzeng, "Accessing suitability of similarity coefficients in measuring human mental models, "Proceedings of the 2012 Network of Ergonomics Society Conference, 2012, pp. 1-5
    連結:
  12. 21.H. Finch, " Comparison of Distance Measure in Cluster Analysis with Dichotomous Data, "Journal of Data Science, vol.3, 2005, pp 85-100
    連結:
  13. 22.S.F. Liang, "Measuring the convergence and accuracy of trainees’ knowledge structures for TFT-LCD visual defect categorization,"International Journal of Industrial Ergonomics, vol.38, 2008,pp. 281-304
    連結:
  14. 23.A.M. Fiore, "The Shopping Experience,"Product Experience, 2008, no.27
    連結:
  15. 24.D. M. Szymanski and R.T. Hise, "E-Satisfaction: An Initial Examination, "Journal of Retailing, 2000, vol. 76, no.3,pp. 309-322
    連結:
  16. 25.R.S. Winer, "A Framework for Customer Relationship Management, "California Management Review, 2001,no. 43, pp. 89-105
    連結:
  17. 26.F.D.Davis,R.P.Bagozzi, and P.R.Warshaw,"User acceptance of computer technology: a comparison of two theoretical models," Management Science, 1989, vol. 35,no. 8, pp. 982-1003
    連結:
  18. 27.F.D Davis, " Perceived usefulness , ease of use and user acceptance of information technology, " MIS Quarterly,1989, vol.13, no. 3 , pp. 319-340
    連結:
  19. 28.V. Venkatesh and F. D. Davis, "A theoretical extension of the technology acceptance model :for longitudinal field studies,"Management Science,2000,vol. 46, no. 2, pp. 186-204
    連結:
  20. 29.D. Baier,E. Stuber, "Acceptance of recommendations to buy in online retailing,"Journal of Retailing and Consumer Services,vol.17, 2010, pp.173-180
    連結:
  21. 3.T. Saracevic," Interactive models in information retrieval : A review and proposal,"Proceedings of the 59th Annual Meeting of the American Society of Information Science, 1996 ,vol. 33, pp. 3-9
  22. 4.P. Borlund,"The concept of relevance in IR,"Journal of the American Society for Information Science and Technology, vol. 54, no.10, 2003, pp. 913-925
  23. 5.S.P. Harter, "Psychological relevance and information science," Journal of the American Society for Information Science, 1992, vol. 43, pp. 132-146
  24. 6.L. Schamber, "User’s criteria for evaluation in a multimedia environment, "Proceedings of the American Society for Information Science, 1991, vol. 28, pp. 126-133
  25. 8.S.M. McNee, I. Albert, D. Cosley, P. Gopalkrishnan, S.K. Lam, A.M. Rashid, J.A. Konstan, and J. Ridel, " On the Recommending of Citations for Research Papers, "Proceedings of the 2002 ACM conference on Computer supported cooperative work, USA, pp. 116-125
  26. 9.U. Hanani, B. Shapira, P. Shoval, "Information filtering: overview of issues, researchand systems, " User Modeling and User-Adapted Interaction 11 , vol.3, 2001, pp.203-259
  27. 15.C. N. Ziegler, S.M. McNee, J.A. Konstan and G. Lausen, " Improving Recommendation Lists Though Topic Diversification, "Proceeding of the 14th international conference on World Wide Web ,Chiba, Japan, ACM : 22-32
  28. 17.G.A.Kelly, The Psychology of personal constructs, New York : W.W.Norton, 1995
  29. 18.M.E. Harper, F.G. Jentsch, D. Berry, H. C. Lau, C. Bowers and E. Sales, "TPL-KATS-card sort:A tool for assessing structural knowledge,"Behavior Research Methods, Instrument,& Computers, vol. 35,no.4,2003,pp. 577-584