Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/24343
標題: 從文章點閱動機與特性分析部落格文章推薦系統的使用者行為
A User Behavior Analysis of Recommendation Schemes in Blogosphere
作者: 林慈儀
Lin, Cih-Yi
關鍵字: 部落格行為
Blog
推薦系統
資訊過濾
Blog reading behavior
recommender system
information filtering
出版社: 資訊管理學系所
引用: [1] A. Tiroshi, T. Kuflik, J. Kay, and B. Kummerfeld, "Recommender Systems and the Social Web", ;in Proc. UMAP Workshops, 2011, pp.60-70. [2] P. Resnick and H.R. Varian, "Recommender Systems - Introduction to the Special Section", ;presented at Commun. ACM, 1997, pp.56-58. [3] J.B. Schafer, D. Frankowski, J.L. Herlocker, and S. Sen, "Collaborative Filtering Recommender Systems", ;in Proc. The Adaptive Web, 2007, pp.291-324. [4] M.J. Pazzani and D. Billsus, "Content-Based Recommendation Systems", ;in Proc. The Adaptive Web, 2007, pp.325-341. [5] B. Smyth, "Case-Based Recommendation", ;in Proc. The Adaptive Web, 2007, pp.342-376. [6] R.D. Burke, "Hybrid Web Recommender Systems", ;in Proc. The Adaptive Web, 2007, pp.377-408. [7] G. Adomavicius and J. Zhang, "Impact of data characteristics on recommender systems performance", ;presented at ACM Trans. Management Inf. Syst., 2012, pp.3-3. [8] Y. Koren, R.M. Bell, and C. Volinsky, "Matrix Factorization Techniques for Recommender Systems", ;presented at IEEE Computer, 2009, pp.30-37. [9] G. Adomavicius and A. Tuzhilin, "Toward the Next Generation of Recommender Systems: A Survey of the State-of-the-Art and Possible Extensions", ;presented at IEEE Trans. Knowl. Data Eng., 2005, pp.734-749. [10] P. Resnick, N. Iacovou, M. Suchak, P. Bergstrom, and J. Riedl, "GroupLens: An Open Architecture for Collaborative Filtering of Netnews", ;in Proc. CSCW, 1994, pp.175-186. [11] B.K. Kaye, “Web Site Story: An Exploratory Study of Why Weblog Users Say They Use Weblogs”, ;in Proc. AEJMC 2005. [12] M. Ryne, “Blogs'' rise stymies old media”, ; http://www.chicago.tribune.com (April 17, 2003) [13] Yao-Jen Chang, Yao-Sheng Chang, Shu-Yu Hsu and Chiu-Hui Chen, “Social Network Analysis to Blog-based Online Community”, ;in Proc. International Conference on Convergence Information Technology, 2007, pp. 2193–2198. [14] T. Lento et al., "The Ties that Blog: Examining the Relationship Between Social Ties and Continued Participation in the Wallop Weblogging System," Proc. Workshop on the Weblogging Ecosystem: Aggregation, Analysis and Dynamics, ACM Press, 2006. [15] S. Hagen, M. Someren and V. Hollink, “Exploration/Exploitation In Adaptive Recommender Systems”, ; The Third European Symposium On Intelligent Technologies, Hybrid Systems And Their Implementation On Smart Adaptive Systems, 2003, pp.189-196. [16] M. Kilfoil, A. Ghorbani, W. Xing, Z. Lei, J. Lu and X. Xu, “Toward An Adaptive Web: The State Of The Art And Science”, ;The 1st Annual Conference On Communication Networks & Services Research, 2003, pp. 238-248. [17] M.P. Chandar, M. Sharma and M.V.V. Saradhi, “Study On Enhancing Blog Quality Using Social Connectivity”, ;International Journal Of Soft Computing And Engineering (IJSCE), Vol. 1, Issue 5, November 2011. [18] R.V. Meteren and M.V. Someren, “Using content-based filtering for recommendation”, ; in Proc. Workshop on Machine Learning and the New Information Age, 2000, pp. 47-56. [19] P.R. Chesnais, M.J. Mucklo and J.A.Sheena, “The Fishwrap personalized news system”, ; in Proc. the Second International Workshop on Community Networking, 1995. [20] U. Shardanand and P. Maes, "Social Information Filtering: Algorithms for Automating "Word of Mouth"", ;in Proc. CHI, 1995, pp.210-217. [21] B.M. Sarwar, G. Karypis, J.A. Konstan, and J. Riedl, "Item-based collaborative filtering recommendation algorithms", ;in Proc. WWW, 2001, pp.285-295. [22] M. Claypool, A. Gokhale, T. Miranda, P. Murnikov, D. Netes, and M. Sartin., “Combining Content-Based and Collaborative Filters in an Online Newspaper”, ; in Proc. the ACM SIGIR ''99 Workshop on Recommender Systems: Algorithms and Evaluation, 1999 [23] M. Balabanovic and Y. Shoham, "Content-Based, Collaborative Recommendation", ;presented at Commun. ACM, 1997, pp.66-72. [24] V.L. Allen, “Situational Factors In Conformity”, ; Advances in Experimental Social Psychology, Vol. 2, 1965, pp.133–175. [25] J. Arndt, “Role of Product-Related Conversation in the Diffusion of a New Product”, ; Journal of Marketing Research, 1965, Vol. 4, pp.291-295. [26] J.J. Brown And P.H. Reingen, "Social Ties And Word-Of-Mouth Referral Behavior," Journal Of Consumer Research, 1987, Vol.14, Issuse 3, Pp.350-362. [27] T.D. Wilson, "Models In Information Behaviour Research", ;Journal Of Documentation, 1997, Vol.55, Issuse 3, pp.249-270. ( Http://Informationr.Net/Tdw/Publ/Papers/1999jdoc.Html) [28] J.B. Schmidt and R. A. Spreng, “A Proposed Model of External Consumer Information Search”, ; Journal of Academy of Marketing Science,1996, Vol. 24, pp.246-256. [29] F. Williams, “Gratifications associated with new communication technologies”, ; In P, Palmgreen, L.A. Wenner, and K.E, Rosengren (Eds.), Media Gratification Research: Current Perspectives, Beverly Hills, Calif.: Sage Publications. [30] N. Srinivasan and B. Ratchford, “An empirical test of a model external search of automobiles”,; Journal of Consumer Research, Vol. 18, No. 2, pp.233-242. [31] J.F. Engel, D.T. Kollat and R.D. Blackwell, Consumer Behavior, the 4th edition, Chicago: Dryden, 1982. [32] W.C. Park, and P. Lessing, “Students and housewive: differences in susceptibility to reference group influence”,; Journal of Consumer Research, September 1977, Vol. 4, pp.102-110. [33] R.J. Vallerand and R. Blssonnette, “Intrinsic, Extrinsic, and Amotivational Styles as Predictors of Behavior: A Prospective Study”,; Journal of Personality, September 1992, Vol. 60, Issue 3. [34] I. Ajzen and M. Fishbein, “Understanding Attitudes and Predicting Social Behavior”,; 1980, Prentice-Hall Press. [35] B.K. Kaye and T. J. Johnson, “A Web for all reasons: Uses and gratifications of Internet resources for political information”. ; Telenzatics and Informatics, Vol. 21(3) pp.197-223. [36] R. Sheizaf, “The Electronic Bulletin Board: A Computer-Driven Mass Medium",; Computer and the Social Sciences, 1986, Vol. 2(3), pp.123-136. [37] B.J. Park and R. E. Plank, “A Use And Gratifications Perspective on the internet as a new information source”,; American Business Review, 2000, Vol. 18(2), pp.43-49. [38] T.F. Stafford and M. R. Stafford, “Identifying Motivations for the use of commercial web sites”,; Information Resources Management Journal, 2001, Vol. 14(1), pp.22-30 [39] A.J. Flanagin and M. J. Metzger, “Internet use in the contemporary media environment”,; Human Communication Rsearch, 2001, Vol. 27, pp.153-181. [40] P. Katerattanakul, “Framework of effective web site design for business-to-consumer internet commerce”, INFOR, 2002, Vol. 40(1), pp.57-70. [41] J. Rodzvilla and R. Blood, “We''ve Got Blog: How Weblogs Are Changing Our Culture”, 2002, Basic Books Publications. [42] J. Hiler, “Blogger’s digest”, MicroContent News. Retrieved June 8, 2003, http://www.microcontentnews.com/article/digests.htm.
摘要: 現今網路發展蓬勃,部落格資訊量日趨增加。能在網際網路中發聲的不再僅限於傳統媒體,個人可擁有自己的部落格、發表個人看法、分享內容與資訊;相較過去,個人部落格上所發表的資訊意見或參考資料,亦開始吸引讀者信任與閱讀觀看。為了能在眾多部落格中讓讀者有效率的閱讀文章,部落格文章推薦系統是能推薦讀者可能有興趣、文章風格符合讀者偏好,或是幫助讀者更快取得更多所需文章的方法。目前推薦系統的資訊過濾方是大致分為內容導向式、協同導向式,或綜合前兩者的混合式。推薦系統與其資訊過濾方式應用於商業網站、社群網站、電子商務網站等多項領域中;應用於不同領域時,會視資訊內容不同,而採用不同參考變數作為推薦的依據,但也因此針對部落格文章讀者所設計的推薦系統則較為少見。若考慮到部落格讀者的閱讀型態、動機與行為,可在設計部落格文章推薦系統時,依讀者型態與動機背景應用不同的參考變數,形成個人化部落格文章推薦。本研究利用問卷調查部落格讀者在不同閱讀動機之下的閱讀型態與行為,透過調查發現在任何閱讀動機之下,文章標題與閱讀動機的相關性為必要條件,但相較於打發時間與社交目的的讀者,搜尋特定資訊的讀者還會另外受到文章評分分數與觀看次數的影響。由調查結論可知,部落格文章評分分數與觀看次數無法在某些閱讀情境作為讀者的推薦依據,但對於那些擁有明確搜尋目地的讀者,例如由特定關鍵字因而閱讀部落格文章的讀者則可做為資訊過濾的參考變數。
The information among blogs is increasing rapidly nowadays. Compare to the information limitation of traditional media press, individuals post their own opinions, articles, messages and information on their own blogs and share to the world. Blog recommender system can help the blogs’ readers read more efficiently. A recommender system recommends posts that readers might interest in or styling is applied to readers’ flavor, and help readers to get information they need quickly. The information filtering of recommender system are content-based filtering, collaborative filtering, and hybrid. The information filtering is applying to business sites, social network sites, or e-commerce websites. According to different types of websites and its contents, information filtering would be composed by different features as filtering factors. Since that, a blog posts recommender system is rare. Considering to the readers’ reading motivations, behavior, or hobbies, those can be the information filtering features of the recommender system, and then to be a personalized blog posts recommender system. This research observed readers’ reading behavior under different reading motivations. It is convinced that the related content between posts and reading motivations is necessary under any circumstances. However, the clicks and scores of posts are only effective to readers searching for certain information or topic contents. The result concludes that the clicks and scores of posts are not reliable as information filtering factors to readers on some situation. But when the readers have certain searching purposes, such like visiting blogs via keyword searching, posts’ scores and clicks could be the filtering factors to generate better blog post recommendations.
URI: http://hdl.handle.net/11455/24343
其他識別: U0005-0102201302520800
文章連結: http://www.airitilibrary.com/Publication/alDetailedMesh1?DocID=U0005-0102201302520800
Appears in Collections:資訊管理學系

文件中的檔案:

取得全文請前往華藝線上圖書館



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.