博碩士論文 etd-0818110-113700 詳細資訊


[回到前頁查詢結果 | 重新搜尋]

姓名 陳建宏(Chien-Hung Chen) 電子郵件信箱 E-mail 資料不公開
畢業系所 資訊管理學系研究所(Information Management)
畢業學位 碩士(Master) 畢業時期 98學年第2學期
論文名稱(中) 利用使用者和產品區隔進行信任為主的推薦之研究
論文名稱(英) Using Trust for Recommendation by Differentiating Users and Products
檔案
  • etd-0818110-113700.pdf
  • 本電子全文僅授權使用者為學術研究之目的,進行個人非營利性質之檢索、閱讀、列印。
    請遵守中華民國著作權法之相關規定,切勿任意重製、散佈、改作、轉貼、播送,以免觸法。
    論文使用權限

    電子論文:校內外都一年後公開

    論文語文/頁數 英文/47
    統計 本論文已被瀏覽 5361 次,被下載 1327 次
    摘要(中) 身處於資訊爆炸的時代,如何快速從網站中有效率地找到所需要的資訊是一件非常困難的事情。對使用者而言,瀏覽、搜尋並決定是否從網路商店中購買產品都是一件費時的工作。因此,許多電子商務網站開始引進推薦機制系統,企圖提供使用者從多樣化的產品與服務中,達到個人客制化的推薦。雖然許許多多的推薦機制方法已經被提出,但是仍然存在許多的問題需要去克服,像是資料稀疏性和新使用者…等相關問題。除此之外,有些學者也發現使用者存在著偏見性、產品存在著可爭議性。我們推測,這些來自於有偏見的使用者、或是對於爭議性的產品所下的評分,可能會對於推薦系統的評估正確性與否造成影響。在這篇論文中,我們將檢驗使用者偏見性和產品爭議性的指標,並提出以信任為基準的推薦機制為做實驗的考量。我們從Epinions.com網站收集信任以及評分資訊作為我
    們實驗的資料。研究結果顯示出,適當調整一些變數,整合使用者偏見性做為調整信任基礎推薦機制的架構後,將達到比較高的推薦正確性。
    摘要(英) Living in the information-overloading age, it is difficult to find the right information and
    identify the resources they need on the websites. As to a user, it is time-consuming in browsing,
    searching, and making a decision to buy products on online stores. Therefore, many
    E-commerce websites have implemented recommender systems that intend to provide users
    with professional recommendation for various types of products and services. Although many
    recommendation methods have been proposed, there are still some problems like the sparsity
    and the cold start problems. In addition, some researchers observe there exist users who are
    biased and products that are controversial. We conjecture that ratings given by biased users or
    given to controversial products may have impact on estimation accuracy of recommendation. In
    this thesis, we will examine the measures for user bias and product controversy and propose
    trust-based-recommendation techniques that take them into account. We evaluate the proposed
    techniques using the web of trust and rating data collected from the Epinions.com website. It is
    found that properly setting some parameters, the proposed trust network-based method that
    incorporates user bias achieve higher recommendation accuracy.
    關鍵字(中)
  • 使用者偏見
  • 電子商務
  • 產品爭議性
  • 信任網路
  • 推薦系統
  • 關鍵字(英)
  • User bias
  • Product Controversy
  • Trust Network
  • Recommender System
  • E-commerce
  • 論文目次 CHAPTER 1 - Introduction.............................................................................. 9
    1.1 Background .....................................................................................................................9
    1.2 Motivation ..................................................................................................................... 10
    CHAPTER 2 - Literature Review .................................................................. 12
    Recommender Systems ....................................................................................................... 12
    2.1.1 Content-based Methods .............................................................................................. 12
    2.1.2 Collaborative Methods ................................................................................................ 14
    2.2 Social Network Analysis ............................................................................................... 16
    2.2.1 The Elements of Social Network ............................................................................. 16
    2.2.2 The Structural Properties of Social Network ........................................................... 17
    2.3 The Trust-Aware Recommendation ............................................................................... 17
    2.3.1 Measuring Trust ...................................................................................................... 18
    2.3.2 Adjusting Trust ....................................................................................................... 18
    2.3.3 Trust Propagation.................................................................................................... 18
    2.3.4 Making Recommendation ....................................................................................... 20
    2.4 Differentiating Users and Products ................................................................................ 20
    2.5 Malicious Users Attack .................................................................................................. 23
    CHAPTER 3 - Recommendations Approaches Based on Trust Network.... 24
    3.1 Problem definition ......................................................................................................... 24
    3.2 The Trust Network Propagation ..................................................................................... 25
    3.3 Differentiating Users and Products ................................................................................ 26
    3.4 Making Recommendation .............................................................................................. 26
    CHAPTER 4 - Experiments............................................................................ 28
    4.1 Data Collection .............................................................................................................. 28
    4.2 Data Set Generation ....................................................................................................... 28
    4.3 Preliminary Experiments ............................................................................................... 29
    4.4 Distribution of User Bias and Product Controversy ........................................................ 34
    4.5 Extend Experiments ....................................................................................................... 37
    4.6 Coverage of Different Thresholds .................................................................................. 40
    4.7 Experiment Using Constant Decline of Bias Users ......................................................... 40
    4.8 Evaluation of Adjusting Collaborative Filtering Method ................................................ 41
    CHAPTER 5 - Conclusion .............................................................................. 43
    References ........................................................................................................ 44
    參考文獻 Adamic, L., & Adar, E. (2003). Friends and neighbors on the web. Social Networks, 25(3), 211-230.
    Adomavicius, G., & Tuzhilin, A. (2005). Toward the next generation of recommender systems: A
    survey of the state-of-the-art and possible extensions. IEEE transactions on knowledge and
    data engineering, 734-749.
    Balabanovi , M., & Shoham, Y. (1997). Fab: content-based, collaborative recommendation.
    Communications of the ACM, 40(3), 72.
    Chirita, P., Nejdl, W., & Zamfir, C. (2005). Preventing shilling attacks in online recommender
    systems. Paper presented at the Proceedings of the 7th annual ACM international workshop
    on Web information and data management.
    De Cock, M., & da Silva, P. (2006). A many valued representation and propagation of trust and
    distrust. Fuzzy Logic and Applications, 114-120.
    Golbeck, J. (2006). Generating predictive movie recommendations from trust in social networks.
    Trust Management, 93-104.
    Golbeck, J. (2009). Trust and nuanced profile similarity in online social networks. ACM
    Transactions on the Web (TWEB), 3(4), 12.
    Golbeck, J., & Hendler, J. (2006). Filmtrust: Movie recommendations using trust in web-based
    social networks. Paper presented at the IEEE Consumer communications and networking.
    Guha, R., Kumar, R., Raghavan, P., & Tomkins, A. (2004). Propagation of trust and distrust. Paper
    presented at the Proceedings of the 13th international conference on World Wide Web.
    Hanneman, R., & Riddle, M. (2005). Introduction to social network methods. Riverside, CA:
    University of California, Riverside.
    Hwang, S., & Chen, L. (2009). Using trust for collaborative filtering in eCommerce.
    Hwang, S., & Chuang, S. (2004). Combining article content and Web usage for literature
    recommendation in digital libraries. Online Information Review, 28(4), 260-272.
    Josang, A. (2007). Trust and reputation systems. Foundations of security analysis and design IV,
    209-245.
    Kautz, H., Selman, B., & Shah, M. (1997). Referral Web: combining social networks and
    collaborative filtering. Communications of the ACM, 40(3), 63-65.
    Krulwich, B., & Burkey, C. (1997). The InfoFinder agent: learning user interests through heuristic
    phrase extraction. IEEE Expert, 12(5), 22-27.
    Lauw, H., Lim, E., & Wang, K. (2006). Bias and controversy: Beyond the statistical deviation.
    Paper presented at the Proceedings of the 12th ACM SIGKDD international conference on
    Knowledge discovery and data mining.
    Lauw, H., Lim, E., & Wang, K. (2008). Bias and Controversy in Evaluation Systems. IEEE
    Transactions on Knowledge and Data Engineering, 1490-1504. 45
    Linden, G., Smith, B., & York, J. (2003). Amazon. com recommendations: Item-to-item
    collaborative filtering. IEEE Internet computing, 7(1), 76-80.
    Massa, P., & Avesani, P. (2004). Trust-aware collaborative filtering for recommender systems. On
    the Move to Meaningful Internet Systems 2004: CoopIS, DOA, and ODBASE, 492-508.
    Massa, P., & Avesani, P. (2005). Controversial users demand local trust metrics: An experimental
    study on epinions. com community. Paper presented at the Proceedings of the 20th national
    conference on Artificial intelligence - Volume 1.
    Massa, P., & Avesani, P. (2007a). Trust-aware recommender systems. Paper presented at the
    Proceedings of the 2007 ACM conference on Recommender systems.
    Massa, P., & Avesani, P. (2007b). Trust metrics on controversial users: balancing between tyranny
    of the majority and echo chambers. International Journal on Semantic Web and Information
    Systems, 3(1), 39-64.
    Massa, P., & Bhattacharjee, B. (2004). Using trust in recommender systems: an experimental
    analysis. Trust Management, 221-235.
    Milgram, S. (1967). The small world problem. Psychology today, 2(1), 60-67.
    Mobasher, B., Dai, H., Luo, T., Sun, Y., & Zhu, J. (2000). Integrating web usage and content mining
    for more effective personalization. Electronic commerce and web technologies, 165-176.
    Mooney, R., & Roy, L. (2000). Content-based book recommending using learning for text
    categorization. Paper presented at the Proceedings of the fifth ACM conference on Digital
    libraries.
    Page, L., Brin, S., Motwani, R., & Winograd, T. (1998). The pagerank citation ranking: Bringing
    order to the web. Stanford InfoLab.
    Pazzani, M. (1999). A framework for collaborative, content-based and demographic filtering.
    Artificial Intelligence Review, 13(5), 393-408.
    Pazzani, M., & Billsus, D. (2007). Content-based recommendation systems. Paper presented at the
    The adaptive web: methods and strategies of web personalization.
    Pazzani, M., Muramatsu, J., & Billsus, D. (1996). Syskill & Webert: Identifying interesting web sites.
    Resnick, P., Iacovou, N., Suchak, M., Bergstrom, P., & Riedl, J. (1994). GroupLens: an open
    architecture for collaborative filtering of netnews.
    Rucker, J., & Polanco, M. (1997). Personalized navigation for the web. Communications of the ACM,
    40(3), 73-75.
    Staab, S., Domingos, P., Mike, P., Golbeck, J., Ding, L., Finin, T., et al. (2005). Social networks
    applied. IEEE Intelligent systems, 20(1), 80-93.
    Victor, P., Cornelis, C., De Cock, M., & Teredesai, A. (2009). A comparative analysis of
    trust-enhanced recommenders for controversial items. Paper presented at the AAAI
    Conference on Weblogs and Social Media 2009.
    Victor, P., Cornelis, C., De Cock, M., & Teredesai, A. (2009). Trust-and distrust-based
    recommendations for controversial reviews. Proc. of WEBSCI09.
    Wang, Y., & Vassileva, J. (2007). Toward trust and reputation based web service selection: A survey.
    Proc. International Transactions on Systems Science and Applications (ITSSA) Journal, 3(2). 46
    Wasserman, S., & Faust, K. (1994). Social network analysis: Methods and applications: Cambridge
    Univ Pr.
    Ziegler, C., & Lausen, G. (2004). Analyzing correlation between trust and user similarity in online
    communities. Trust Management, 251-265.
    口試委員
  • 林福仁 - 召集委員
  • 楊婉秀 - 委員
  • 黃三益 - 指導教授
  • 口試日期 2010-06-29 繳交日期 2010-08-18

    [回到前頁查詢結果 | 重新搜尋]


    如有任何問題請與論文審查小組聯繫