跳到主要內容

臺灣博碩士論文加值系統

(216.73.216.152) 您好!臺灣時間:2025/11/02 15:35
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:唐紫瑞
研究生(外文):Tzu-Jui Tang
論文名稱:以使用者為中心的推薦系統架構-以線上購物為例
論文名稱(外文):The Framework of Customer-Centric Recommender Systems - an on-line shopping model
指導教授:顏昌明顏昌明引用關係
指導教授(外文):Chang-Ming Yan
學位類別:碩士
校院名稱:銘傳大學
系所名稱:資訊管理學系碩士班
學門:電算機學門
學類:電算機一般學類
論文種類:學術論文
論文出版年:2009
畢業學年度:97
語文別:中文
論文頁數:91
中文關鍵詞:隱私電子商務使用者中心推薦系統
外文關鍵詞:E-CommercePrivacyCustomer-CentricRecommender Systems
相關次數:
  • 被引用被引用:4
  • 點閱點閱:627
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:1
電子商務的興起,改變了過去的交易模式,消費者透過網路取得大量且透明化的商品資訊,在這樣的模式下,消除了過去資訊不對稱的情形,卻也帶來了資訊泛濫的問題。網路上大量的資訊,造成使用者在搜尋和比較商品上的困擾,加上網路購物市場的競爭激烈,商家開始發展各種的應用技術,來取得消費者的青睞,而推薦系統的技術正是其應用之一。在傳統的推薦架構中,由於推薦系統多依附於商家的購物網站之下,使用者若想得到系統的推薦結果,就必須先提供個人資料或偏好供系統做長期追蹤,再透過各種資訊技術的分析後,產生適當的推薦商品給使用者。
然而,在傳統的兩層式推薦架構中,由於商家間的資訊無法互通,當使用者進入到未曾到訪的購物網站時,就必須重新讓系統進行資料的蒐集與分析,才有可能得到適當的推薦結果。而與使用者相關的各種資料,會因使用者曾經購買或使用的網站多寡,而分散在網路上的各個角落。在這樣的狀況下,除了會降低推薦系統的推薦能力外,也增加了使用者隱私被侵犯的風險。
因此,本研究提出一個三層式的推薦架構,包含使用者、伺服器與商家,使推薦系統不需依附於商家之下,由使用者自行集中累積與個人相關的資料(如:購買記錄、個人偏好等),再透過中介伺服器的協助,至不同的商家進行商品的搜尋。最後,由位於使用者端的系統產生適當的推薦結果,以作為使用者購買決策上的參考。透過這樣的架構,來改善過去推薦系統無法提供跨商家的推薦服務,以及使用者剛進入到新系統中無法得到推薦結果的狀況。此外,藉由這種架構的改變,來降低使用者在推薦過程中,受到隱私侵犯的風險。
本研究針對所提架構進行雛型系統的開發,並透過實驗室實驗法及問卷進行驗證。從30個有效樣本的結果中發現,參與者對實驗中的兩個商家,無論在第一個或第二個商家上,對本系統結果的個人化推薦滿意度平均值,皆高於原始系統結果的平均值。而隨著使用者在個人端累積來自不同商家的購買偏好資訊越多,使用者對於本系統和原使系統的滿意度差異程度也隨之更高。此外,使用對本系統的隱私保護以及系統整體滿意度上,也都有一定程度以上的表現。
With the blooming of E-Commerce, the traditional business models have been changed. Consumers nowadays can obtain enormous of product information through the Internet. This model has successfully rectified the situation of asymmetric information which was prevalent in the past, but it has also brought about the problems of information overflow. The huge amount of information on the Internet has confused users who are searching and comparing goods on-line. Besides, due to the keen competition of the online shopping markets, online store owners have embarked on developing various applications to appeal to the consumers. One of such applications is the Recommender Systems (RS). In the traditional RS framework, because the system is usually built within a shopping website, users who want to receive the results of the recommendation have to provide their personal information or preference for the system to do the long-term tracking. The suitable products will then be recommended to the users after the data analysis.
However, in the traditional two layers RS framework, the information between different stores cannot be shared; thus, when users visit a new shopping website, they have to key-in their personal data in the system again so that they can get the recommendation. In this way, the more websites users visit or shop on, the more likely it is that their personal information will be disclosed. Under such circumstance, not only does the effect of the recommender system be reduced, but the risks of user privacy invasion also increase.
This research proposes a three layers RS framework includes user’s PC, Web server and on-line Purchase Website subsystems. This new RS does not need to be built within the shopping websites. Instead, users can first collect relevant information such as purchasing records and personal preference and go to different on-line stores to do the product searching with the help of an intermediary server. Then the recommendation result will be generated from the users’ personal computers. By this new RS framework, it can improve traditional RS framework which cannot provide cross-sellers'' recommendations, and avoid the user who is new to the system without any recommendation result. In addition, with this new framework, the risks of user privacy violation will also be lowered.
Base on aforementioned framework, a new prototype system is developed and verified through laboratory experiments and questionnaires. The results of thirty valid samples reveal that the participants are much more satisfied with this new RS than the traditional ones. As a user’s personal information will be accumulated in each transaction from different stores into his own computer. It also shows that the users who experienced the transaction more times have the higher satisfaction comparing to the first one usage. Therefore, this new RS framework well performed in both of the privacy protection and the satisfaction degree on system itself as well.
中文摘要_______________________i
英文摘要_______________________ii
誌 謝_______________________iv
目 錄_______________________v
表 目 錄_______________________vii
圖 目 錄_______________________viii

第壹章 緒論___________________1
第一節 研究背景_______________1
第二節 研究動機_______________3
第三節 研究目的_______________6
第四節 研究範圍與限制_________8
第五節 研究流程_______________9

第貳章 文獻探討_______________10
第一節 推薦系統_______________10
一、 推薦系統的定義___________10
二、 推薦系統的分類___________10
三、 小結_____________________16
第二節 隱私權_________________17
一、 隱私權的定義_____________17
二、 隱私保護_________________18
三、 推薦系統隱私_____________20
四、 小結_____________________21
第三節 多準則決策法___________22
一、 多準則決策的基本概念_____22
二、 層級分析法_______________23
第四節 使用者滿意度評估_______27
一、 使用者隱私感知評估_______27
二、 使用者滿意度評估_________27

第参章 研究方法_______________28
第一節 系統架構_______________28
一、 傳統的推薦系統架構與流程_28
二、 本研究系統架構與流程_____31

第二節 系統設計_______________37
一、 個人偏好設定_____________37
二、 個人化推薦_______________38
第三節 實驗設計_______________43
一、 實驗方法_________________43
二、 實驗對象_________________43
三、 實驗流程_________________44
第四節 問卷設計_______________47

第肆章 結果分析與討論_________52
第一節 實驗系統_______________52
一、 登入_____________________53
二、 偏好設定_________________53
三、 個人化推薦系統___________55
第二節 實驗結果與討論_________57
一、 樣本結構分析_____________57
二、 信效度分析_______________61
三、 推薦系統個人化分析_______63
四、 系統隱私保護感知度分析___67
五、 系統滿意度分析___________68

第伍章 結論與建議_____________70
第一節 結論___________________70
第二節 後續研究建議___________73
一、 樣本資料與實驗操作_______73
二、 實驗商家_________________73
三、 系統設計_________________73

參考文獻_______________________75
附錄一 問卷____________________79
中文文獻:
林秀宜,網站經營對於顧客資訊隱私保護觀之研究,國立高雄第一科技大學資訊管理系碩士論文,民國93年。
吳明隆、涂金堂,SPSS與統計應用分析(修訂版),台北市:五南圖書出板股份有限公司,民國95年。
梁定澎,決策支援系統與企業智慧(再版),Decision support systems and business intelligence,臺北市:智勝文化,民國95年。
資策會MIC(2007),2007年台灣電子商店發展趨勢,資策會出版。
鄧振源,運籌規畫與研究中心系列叢書T001計劃評估方法與應用第二版,台北:規劃運籌管理,民國94年。
鄧振源、曾國雄,「層級分析法的內涵特性與應用上」,中國統計學報,第27卷,第6期,民國78年,頁6~22。
簡媜富,決策分析與管理:全面決策品質提升之架構與方法,台北:雙葉書廊有限公司,民國94年,初版。
蘇宏文,資訊隱私大護法,臺北市:法律與你雜誌社,民國85年。
顧宜錚,影響網路商店推薦商品購買意願之因素,國立中山大學資訊管理學系研究所博士論文,民國93年。


英文文獻:
Adomavicius, G., and Tuzhilin, A. "An Architecture of e-Butler: A Consumer-Centric Online Personalization System," in: International Journal of Computational Intelligence & Application, World Scientific Publishing Company, 2002, p. 313.
Bakabanovi, M., and Shoham, Y. "Fab: Content-Based, Collaborative Recommendation," Communications of the ACM (40:3) 1997, pp 66-72.
Berendt, B., Gunther, O., and Spiekermann, S. "Privacy in E-commerce: Stated Preferences vs. Actual Behavior," Communications of the ACM (48:4) 2005, pp 101-106.
Bo, X., and Benbasat, I. "E-commerce Product Recommendation Agent: Use, Characteristic and Impact," MIS Quarterly (31:1), 03 2007, pp 137-209.
Bridge, D., Goker, M.H., McGinty, L., and Smyth, B. "Case-based recommender systems," Knowl. Eng. Rev. (20:3) 2005, pp 315-320.
Cissee, R., and Albayrak, S. "An agent-based approach for privacy-preserving recommender systems," in: Proceedings of the 6th international joint conference on Autonomous agents and multiagent systems, ACM, Honolulu, Hawaii, 2007.
Cranor, L.F. "Internet Privacy. (cover story)," Communications of the ACM (42:2) 1999, pp 28-31.
Doll, W.J., and Torkzadeh, G. "The Measurement of End-User Computing Satisfaction," MIS Quarterly (12:2) 1988, pp 259-274.
Good, N., Schafer, J.B., Konstan, J.A., Borchers, A., Sarwar, B., Herlocker, J., and Riedl, J. "Combining collaborative filtering with personal agents for better recommendations," in: Proceedings of the sixteenth national conference on Artificial intelligence and the eleventh Innovative applications of artificial intelligence conference innovative applications of artificial intelligence, American Association for Artificial Intelligence, Orlando, Florida, United States, 1999.
Hwang, C.-L., and Kwangsum, Y. Multiple Attribute Decision Making : Methods and Applications Springer-Verlag, New York, 1981.
Iachello, G., and Hong, J. "End-User Privacy in Human-Computer Interaction," Foundations and Trends® in (1:1) 2007, pp 1-137.
Liang, T.-P., Hung-Jen, L.A.I., and Yi-Cheng, K.U. "Personalized Content Recommendation and User Satisfaction: Theoretical Synthesis and Empirical Findings," in: Journal of Management Information Systems, M.E. Sharpe Inc., 2006, pp. 45-70.
Linn, J. "Technology and Web User Data Privacy: A Survey of Risks and Countermeasures," IEEE Security and Privacy (3:1) 2005, pp 52-58.
Mason, R.O. "Four Ethical Issues of the Information Age," MIS Quarterly (10:1) 1986, pp 5-12.
Mobasher, B., Cooley, R., and Srivastava, J. "Automatic personalization based on Web usage mining," Commun. ACM (43:8) 2000, pp 142-151.
Montaner, M., Lopez, B., and Rosa, J.L.D.L. "A Taxonomy of Recommender Agents on the Internet," Artif. Intell. Rev. (19:4) 2003, pp 285-330.
Price, B.A., Adam, K., and Nuseibeh, B. "Keeping ubiquitous computing to yourself: A practical model for user control of privacy," International Journal of Human-Computer Studies (63:1-2) 2005, pp 228-253.
Resnick, P., and Varian, H.R. "Recommender Systems," Communications of the ACM (40:3) 1997, pp 56-58.
Saaty, T.L. "A scaling method for priorities in hierarchical structures," Journal of Mathematical Psychology (15:3) 1977, pp 234-281.
Saaty, T.L. "The Analytic Hierarchy Process," New York: McGraw-Hill) 1980.
Schafer, J.B., Konstan, J.A., and Riedl, J. "E-Commerce Recommendation Applications," Data Min. Knowl. Discov. (5:1-2) 2001, pp 115-153.
Smith, H.J., Milberg, S.J., and Burke, S.J. "Information Privacy: Measuring Individuals'' Concerns About Organizational Practices," MIS Quarterly (20:2), 06 1996, pp 167-196.
Stohr, E.A., and Viswanathan, S. "Recommendation Systems: Decision Support for the Information Economy," Information Systems Working Papers Series.
Tuzhilin, A. "The E-Butler Service, or Has the Age of Electronic Personal Decision Making Assistants Arrived?," Information Systems Working Papers Series.
Wang, H., Lee, M.K.O., and Wang, C. "Consumer Privacy Concerns about Internet Marketing," Communications of the ACM (41:3) 1998, pp 63-70.
Warren, S.D., and Brandeis, L.D. "The Right to Privacy," Harvard Law Review (4:5) 1890, pp 193-220.


網路文獻:
Netflix(2009),”Netflix Prize Leaderboard”,<http://www.netflixprize.come/lead rboard>(存取時間:2009年7月22日)。
Read Write Web(2009),” MyStrands Offers $100k for Best Recommender Start-up”<http://www.readwriteweb.com/archives/mystrands_offers_100k_for_best_recommender_startup.php>(存取時間:2009年7月22日)。
中央社(2009),” 資策會估2009年台灣網購商機達3116億元”,<http://www.cna.com.tw/SearchNews/doDetail.aspx?id=200907140238>(存取時間:2009年7月15日)。
台灣網路資訊中心(2009),"九十八年度台灣寬頻網路使用調查報告",全國意向顧問股份有限公司<http://www.twnic.net.tw/download/200307/200307index.shtml>(存取時間:2009年7月15日)。
資策會MIC (2008),”台灣線上購物市場發展趨勢”,<http://mic.iii.org.tw/intelligence/search/pop/show_graph_all.asp?pptno=PPT971029-3>(存取時間:2009年8月15日)。
遠見雜誌(2009),“一年只花1375元買書 450萬成人不看書,台灣怎來競爭力”,<http://www.gvm.com.tw/Forum/Content.aspx?ser=13277>(存取時間:2009年7月15日)。
電子全文 電子全文(本篇電子全文限研究生所屬學校校內系統及IP範圍內開放)
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top