隨著網路的快速發展，網拍近年來也隨之興起，而在網路上購物，評價一直都是個最有效的指標，提供買賣雙方做為參考。買家在購買產品後，能透過評價機制作為回饋，反應對賣家的滿意度。此外，賣家的評價反映過去的交易歷史，正評價越多，表示成功且令人滿意的交易越多，也代表了賣家信用的累積。
本研究採用創新擴散模式，利用實際的數據，分析賣家的評價趨勢、關鍵評價量，並以群聚分析將賣家進行分類和進一步討論。其樣本來自於eBay上的t-shirt賣家，資料蒐集時間從2010年12月1日到2011年1月31日，總共收集8304個賣家，再隨機挑選出116個符合我們研究要求的賣家。
本研究主要回答了三個研究問題。第一個研究問題是要驗證評價符合創新擴散模式，並可用該模式分析與討論其評價增長和成長趨勢。研究結果證實了評價的增長符合創新擴散模式，且成長趨勢也符合S曲線。此外，如果評價是受到外部的影響，例如：關鍵字廣告、網站付費廣告等，則評價在一開始的累積速度會較快。反之，如果是受到內部影響較高，例如：口耳相傳，則是在一段時間後，因為名聲的建立，賣家的成長幅度會大幅提升。
第二個研究問題則是要以貝斯模式計算賣家的關鍵評價量。研究結果顯示，賣家的關鍵評價量介於1129至1402時，表示其累積了一定的銷售額與客戶的滿意度，也讓潛在買家更加相信並提高購買的意願，此時評價的累積就會更加的快速。此外，也可以代表當賣家到達關鍵評價量時，已累積一定的經驗，提供了更好的行銷策略。
第三個研究問題是將賣家進行群聚分析與討論。研究結果發現，不論是其評價成長趨勢、關鍵評價量與到達所需時間、產品價格，甚至是買家的再次回購率，都是有相當顯著的差異性。本研究可以提供新手買家做為參考，使其依據其產品發展屬於自己的行銷策略。

With the rapid Internet development, E-auction is also popular in recent years. In E-auction, the rating is the most effective indicator that can provide a referral for buyer and seller. In addition, buyers can use rating mechanism as feedback to respond their satisfaction after they bought goods. In the other hand, the rating of seller could reflect his transaction history before. When the positive rating is more, which means satisfied and successful transaction is more also, and represents that seller’s credit accumulation.
This study uses innovation diffusion model to analyze the seller’s growth trend of rating, critical mass of rating by real data, classify sellers that equal to cluster analysis and discuss further. The samples are the sellers who sell t-shirt in eBay from December 1 in 2010 to January 31 in 2011. We get 8,304 sellers’ data, and pick 116 of them randomly as samples, which are fit in with our research requests.
This research is to answer three research questions. The first research question is to verify that growth trend of rating could fit in with diffusion of innovation, then, to analyze and discuss the growing trend and the rating accumulation. That result does verify that rating accumulation fit in with diffusion of innovation, and growing trend fit in with S-shaped curve. Furthermore, rating raise at first if it is affected by external influence, like key searching, website payment advertisement. On the contrary, the rating increases quickly for some time that the seller has good reputation if the rating is affected by internal influence, like word of mouth.
The second research question is to calculate the critical mass of rating by Bass model. The result shows that the rating accelerates when it reaches critical mass between 1129 and 1402, it represents the seller accumulates considerable sale amount and customer satisfaction, and also let potential buyers more confident and promote their willingness to purchase. In addition, it can represent the sellers have enough experience and can provide the better marketing strategies when the sellers’ rating reaches critical mass of rating.
The third research question is to divide the sellers by cluster analysis and investigate. The result shows the diverseness between the growth trend of rating, the critical mass of rating, product price, and buyer repeated purchase.
This study can provide a referral for the novice sellers, and they can develop their marketing strategy base on their characteristics of product.

Chapter 1. Introduction 1
Chapter 2. Literature Review 5
2.1 E-auction and seller’s rating 5
2.2 Diffusion models of innovation and seller rating 9
2.3 Critical Mass 12
2.4 Cluster Analysis 14
Chapter 3. Research Methodology 16
3.1 Research Design 16
3.2 Data Collection 17
3.2.1 Data Sources 17
3.2.2 Process of Data Collection 17
3.2.3 Data Statement 19
3.2.4 Data Selection 21
Chapter 4. Bass Model fitting and Critical Mass 23
4.1 Bass Model fitting and Critical Mass 23
4.1.1 Bass Model fitting 23
4.1.2 Critical Mass 26
4.2 Four examples 27
4.2.1 Integration introduction for four examples 27
4.2.2 Description for each example 30
Chapter 5. Cluster Analysis 39
5.1 The Cluster Analysis for Innovation and Imitation Coefficient of Bass Model 39
5.2 The Characteristic of Each Cluster 42
5.2.1 Cluster1 –high imitation and high innovation 42
5.2.2 Cluster2 –medium innovation and medium imitation 44
5.2.3 Cluster3 - low imitation and low innovation 46
5.2.4 Cluster4 - high imitation and low innovation 48
Chapter 6. Discussions and Conclusions 50
6.1 Academic Implications 50
6.2 Practical Implications 50
6.3 Conclusions 51
6.4 Research Limitation 52
6.5 Future Research 52
References 54
Appendix 56

Ariely, D., & Simonson, I. (2003). Buying, bidding, playing, or competing? Value assessment and decision dynamics in online auction. Journal of Consumer Psychology, 13(1&2), 113–123.
Ba, S., & Pavlou, P. A. (2002). Evidence of the effect of trust building technology in electronic markets: Price premiums and buyer behavior. MIS quarterly, 243-268.
Bass, F. M. (1969). Bass. A new product growth for model consumer durables. Management Science, 15(5), 215-227.
Becherer, R. C., & Halstead, D. (2004). Characteristics and internet marketing strategies of online auction sellers. International Journal of Internet Marketing and Advertising, 1(1), 24-37.
Becherer, R. C., Halstead, D., & Taylor, A. J. (2008). Auction characteristics and outcomes: An empirical examination of eBay. Journal of Internet Commerce, 7(3), 403-424.
Bruce, N., Haruvy, E., & Rao, R. (2004). Seller rating, price, and default in online auctions. Journal of Interactive Marketing, 18(4), 37-50.
Chen, T. W. (2010). The Growth Trend of E-Auction Seller's Ratings – An Application of the Diffusion Model. Paper presented at the The 16th Cross Straits Information Management Conference.
Dholakia, U. M. (2005). The usefulness of bidders' reputation ratings to sellers in online auctions. Journal of interactive marketing, 19(1).
Farias, V., Lewis, T., & Long, B. (2009). Case analysis studies of diffusion models on E-commerce transaction data. Massachusetts Institute of Technology.
Fourt, L. A., & Woodlock, J. W. (1960). Early prediction of market success for new grocery products. The Journal of Marketing, 25(2), 31-38.
Griliches, Z. (1957). Hybrid corn: An exploration in the economics of technological change. Econometrica, Journal of the Econometric Society, 25(4), 501-522.
Hayne, S. C., Smith, C. A. P., & Vijayasarathy, L. R. (2003). Who wins on eBay: an analysis of bidders and their bid behaviours. Electronic Markets, 13(4), 282-293.
Houser, D., Wooders, J., & Hall, M. C. (2006). Reputation in auctions: Theory, and evidence from eBay. Journal of Economics & Management Strategy, 15, 353-369.
Jang, S. L., Dai, S. C., & Sung, S. (2005). The pattern and externality effect of diffusion of mobile telecommunications: the case of the OECD and Taiwan. Information Economics and Policy, 17(2), 133-148.
Kauffman, R. J., & Wood, C. A. (2006). Doing their bidding: An empirical examination of factors that affect a buyer’s utility in Internet auctions. Paper presented at the Information Technology and Management.
Kim, M. S., & Kim, H. (2004). Innovation diffusion of telecommunications: general patterns, diffusion clusters and differences by technological attribute. INTERNATIONAL JOURNAL OF INNOVATION MANAGEMENT., 8, 223-241.
Lee, Z., Im, I.,, & Lee, S. J. (2006). The effect of buyer feedback scores on Internet auction prices. Journal of Organizational Computing and Electronic Commerce, 16(1), 51-64.
Lin, F. H. (2011). The Growth Trend and Cluster Analysis of E-Auction Seller Ratings. Paper presented at the e-CASE & e-Tech 2011.
Mansfield, E. (1961). Technical change and the rate of imitation. Econometrica: Journal of the Econometric Society, 29(4), 741-766.
McDonald, C. G., & Slawson Jr, V. C. (2002). Reputation in an internet auction market. Economic Inquiry.
Pavlou, P. A., & Gefen, D. (2004). Building effective online marketplaces with institution-based trust. Information Systems Research, 15(1), 37-59.
Reiley, D., Bryan, D., Prasad, N., Reeves, D., Hall, M., Engines, K. E., et al. (2007). Pennies from eBay: The determinants of price in online auctions. Journal of Industrial Economics, 55(2), 223-233.
Resnick, P., Kuwabara, K., Zeckhauser, R., & Friedman, E. (2002). Reputation systems. Communications of the ACM, 43(12), 45-48.
Reynolds, K. E., Gilkeson, J. H., & Niedrich, R. W. (2009). The influence of seller strategy on the winning price in online auctions: A moderated mediation model. Journal of Business Research, 62(1), 22-30.
Sen, R., King, R. C., & Shaw, M. J. (2006). Buyers' choice of online search strategy and its managerial implications. Journal of Management Information Systems, 23(1), 211-238.
Shmueli, G., Patel, N. R., & Bruce, P. C. (2007). Data mining for business intelligence: John Wiley & Sons.
Standifird, S. S. (2001). Reputation and e-commerce: eBay auctions and the asymmetrical impact of positive and negative ratings. Journal of Management, 27(3), 279.
Teng, J. T. C., Grover, V., & Guttler, W. (2002). Information technology innovations: General diffusion patterns andits relationships to innovation characteristics. IEEE Transactions on Engineering Management, 49(1), 13-27.
Valente, T. (1995). NetworkModels of theDiffusion of Innovations. Creskill, NJ:Hampton Press.