請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/60429
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 廖婉君(Wanjiun Liao) | |
dc.contributor.author | Yen-Kai Huang | en |
dc.contributor.author | 黃焱鍇 | zh_TW |
dc.date.accessioned | 2021-06-16T10:17:57Z | - |
dc.date.available | 2018-08-28 | |
dc.date.copyright | 2013-08-28 | |
dc.date.issued | 2013 | |
dc.date.submitted | 2013-08-17 | |
dc.identifier.citation | [1] P. Resnick and H.Varian. Recommender systems. Communications of the ACM, 40(3):56–58, 1997.
[2] G. Linden, B. Smith, and J. York. Amazon. com recommendations: Item-to-item collaborative filtering. Internet Computing, IEEE, 7(1):76–80, 2003. [3] B. Sarwar, G. Karypis, J. Konstan, and J. Riedl. Item-based collaborative filtering recommendation algorithms. In Proceedings of the 10th international conference on World Wide Web, pages 285–295. ACM, 2001. [4] G. Adomavicius and A. Tuzhilin. Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions. Knowledge and Data Engineering, IEEE Transactions on, 17(6):734–749, 2005 [5] Z Huang, W. Chung, T. H. Ong, and H. Chen, A graph-based recommender system for digital library. In Proceedings of the 2nd ACM/IEEE-CS joint conference on Digital librariesm, pages 65-73. 2002, ACM. [6] BURKE, Robin. Hybrid recommender systems: Survey and experiments. User modeling and user-adapted interaction, 2002, 12.4: 331-370. [7] X. Su, and Taghi M. Khoshgoftaar. A survey of collaborative filtering techniques. Advances in artificial intelligence 2009: 4. [8] Lichtenwalter, R. N., Lussier, J. T., & Chawla, N. V. , New perspectives and methods in link prediction. In Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining (pp. 243-252). ACM, 2010. [9] Sun, Y., Han, J., Yan, X., Yu, P. S., & Wu, T.. Pathsim: Meta path-based top-k similarity search in heterogeneous information networks. VLDB, 2011.. [10] G. Karypis. Evaluation of item-based top-n recommendation algorithms. In Proceedings of the tenth international conference on Information and knowledge management, pages 247–254. ACM, 2001. [11] J. L. Herlocker, J. A. Konstan, L. G. Terveen, and J. T. Riedl. Evaluating collaborative filtering recommender systems. ACM Transactions on Information Systems (TOIS), 22(1):5–53, 2004. [12] P. Cremonesi, Y. Koren and R. Turrin, Performance of recommender algorithms on top-n recommendation tasks. In Proceedings of the fourth ACM conference on Recommender systems, pages 39—46. ACM, 2010. [13] M. Jamali and M. Ester. Trustwalker: a random walk model for combining trustbased and item-based recommendation. In Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining, pages 397–406. ACM, 2009. [14] M. Jamali and M. Ester. Using a trust network to improve top-n recommendation. In Proceedings of the third ACM conference on Recommender systems, pages 181–188. ACM, 2009. [15] J. O’Donovan and B. Smyth. Trust in recommender systems. In Proceedings of the 10th international conference on Intelligent user interfaces, pages 167–174. ACM, 2005. [16] J. A. Golbeck. Computing and applying trust in web-based social networks. 2005. [17] P. Massa and P. Avesani. Trust-aware recommender systems. In Proceedings of the2007 ACM conference on Recommender systems, pages 17–24. ACM, 2007. [18] Y. Koren, S. C. North, and C. Volinsky. Measuring and extracting proximity in networks. In Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining, pages 245–255. ACM, 2006. [19] H. H. Song, T. W. Cho, V. Dave, Y. Zhang, and L. Qiu. Scalable proximity estimation and link prediction in online social networks. In Proceedings of the 9th ACM SIGCOMM conference on Internet measurement conference, pages 322–335. ACM, 2009. [20] Leo Katz. A new status index derived from sociometric analysis. Psychometrika, 18(1):39-43, 1953. [21] H. Tong, C. Faloutsos, and Y. Koren. Fast direction-aware proximity for graph mining. In Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining, pages 747–756. ACM, 2007. [22] D. Liben-Nowell and J. Kleinberg. The link-prediction problem for social networks. Journal of the American society for information science and technology, 58(7):1019–1031, 2007. [23] Yildirim, H., & Krishnamoorthy, M. S, A random walk method for alleviating the sparsity problem in collaborative filtering. In Proceedings of the 2008 ACM conference on Recommender systems (pp. 131-138). ACM, 2008. [24] Page, L., Brin, S., Motwani, R., & Winograd, T.. The PageRank citation ranking: bringing order to the web, 1999. [25] M. Newman, A.-L. Barabasi, and D. J. Watts. The structure and dynamics of networks. Princeton University Press, 2011. [26] D. J. Watts and S. H. Strogatz. Collective dynamics of ‘small-world’ networks. nature, 393(6684):440–442, 1998 [27] J. Saramaki,, M. Kivela,, J. P. Onnela,, K. Kaski,, & J. Kertesz,Generalizations of the clustering coefficient to weighted complex networks. Physical Review E, 75(2), 027105. 2007. [28] X. Yang, H. Steck, Y. Guo, and Y. Liu. On top-k recommendation using social networks. In Proceedings of the sixth ACM conference on Recommender systems, pages 67–74. ACM, 2012. [29] J. Bobadilla, F.Ortega, A. Hernando, and J. Bernal, A collaborative filtering approach to mitigate the new user cold start problem. Knowledge-Based Systems, vol. 26, pages 225-238. 2012 | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/60429 | - |
dc.description.abstract | 協同過濾是目前推薦系統中最廣為運用的方法之一。針對在推薦系統中更為符合產業需求的前k項之項目推薦為目標,利用信任關係建立社群親近度、並融合了使用者相似度來加強推薦系統準確度。此研究提出一個基於圖形基礎的協同過濾架構。基於考量使用者在資料中的變異性個人化,針對每一個使用者在資料中的表現建立自我網路,並且分為社群相近度層、相似使用者層以及相似項目層,我們進而發展預測各層的信心指數的機制:利用網路科學的理論基礎─群聚係數,分析各層內物件所組成的圖的相似性,以判斷使用者在系統上行為的一致性,藉而估計出對於此層推薦路徑的可信度。最後以可信度融合三層的推薦路徑以預測該使用者之後可能評分的項目對象,產生出前k項之推薦結果。我們利用來自真實世界社群網路服務中的資料,研究各參數以及相似度計算的設定在不同服務的資料庫中的表現及對推薦結果準確度的影響。實驗顯示,基於此圖形架構下的融合機制可以有效地彌補不同方法之間的缺漏,增加推薦名單的命中準確性,並可從推薦路徑中提供使用者對於推薦結果的解釋,以增進推薦系統中的使用者經驗。 | zh_TW |
dc.description.abstract | Collaborative filtering is one of the most widely used memory-based approaches in recommender systems. CF uses the known preferences of a group of users to recommend or predict the unknown preferences for other users. Top-n item recommendation is an important tasks for recommendation and more realistic than value prediction for e-commerce system design. To improve the accuracy performance of recommendation, in the thesis we first introduce the trust into the system and exploit proximity to enhance CF. Second, we propose a general graph probabilistic model fusing item-based, user-based and proximity-based collaborative filtering by path ensemble from three layers. The model is consequently more robust to data sparsity. Further, to deliberate the confidence from these three sources, based on the framework we propose the CCR estimation mechanism to weigh the importance between each predictor of layer graphs. The mechanism exploits the classic network property, clustering coefficient, on ego network of target user by the simple intuition of consistency of user behavior. To evaluate the different predictors, the hit ratio metric is proposed to measure the accuracy quality of fusion of predictors. Experiments on real datasets demonstrate that the proposed methods are indeed more effective against accuracy. The results show the fusion by CCR estimation mechanism can improve the recall performance and hit ratio of fusion on the both datasets. Thus, the accuracy and diversity requirement could be achieved in the same time. The experiments also show that the fusion predictor contains proximity based CF is helpful especially on the cold users. Besides, the proposed graph-based framework is able to provide the explanation by the recommendation path, the user experience of the system could be promoted. | en |
dc.description.provenance | Made available in DSpace on 2021-06-16T10:17:57Z (GMT). No. of bitstreams: 1 ntu-102-R00921088-1.pdf: 2941699 bytes, checksum: 95e03e151f7ba8bb2205f012ff41e92a (MD5) Previous issue date: 2013 | en |
dc.description.tableofcontents | 口試委員會審定書 #
誌謝 i 中文摘要 iii ABSTRACT iv CONTENTS v LIST OF FIGURES viii LIST OF TABLES ix Chapter 1 Introduction 1 1.1 Collaborative Filtering in Recommender System 2 1.2 Social Trust and Proximity 5 1.3 Graph-based Collaborative Filtering and Unification 7 1.4 Top-k Recommendation 9 1.5 Contributions 10 1.6 Thesis Organization 11 Chapter 2 Literature Review 13 2.1 Collaborative Filtering 13 2.2 Trust and Social Networks 13 2.3 Graph-based Recommendation and Unification 15 Chapter 3 Preliminaries 17 3.1 Similarity Computation 17 3.1.1 Rating Difference Similarity 17 3.1.2 Neighborhood Structural Similarity 19 3.2 Top-k Recommendation Problem 19 Chapter 4 Model and Framework 21 4.1 Ego Network 21 4.1.1 Ego Network by Similarity 21 4.1.2 Ego Network by Trust 22 4.1.3 Framework Adoption 23 4.2 Graph-based Framework 24 4.2.1 Item- and user-based CF on the Framework 25 4.2.2 Proximity-based CF on the Framework 26 4.3 RecPath Analysis 27 4.4 CCR-based Fusion Collaborative Filtering 31 4.4.1 Fusion Collaborative Filtering 31 4.5 Consistency Confidence Ratio Estimation 33 4.6 Process of CCR-based Fusion CF 36 Chapter 5 Experiments 39 5.1 Dataset Description 39 5.2 Testing Methodology 40 5.3 Evaluation Metrics 41 5.4 Experimental Results 43 5.4.1 Social Network Graph Property 43 5.4.2 Neighborhood Size of ULG 44 5.4.3 Recall of Single Layer Predictors 46 5.4.4 Recall of FLG by CCR Estimation Mechanism 48 5.4.5 Hit Ratio on Predictor of Fusion 50 5.4.6 Experiments on Cold Users - Sparsity Problem 52 Chapter 6 Conclusion and Future Works 55 6.1 Future Works 55 6.2 Conclusion 56 REFERENCE 58 | |
dc.language.iso | en | |
dc.title | 於圖形基礎之協同過濾架構上融和信任關係與相似度之Top-k項目推薦 | zh_TW |
dc.title | Fusing Trust and Similarity on Graph-based Collaborative Filtering Framework for Top-k Item Recommendation | en |
dc.type | Thesis | |
dc.date.schoolyear | 101-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 張正尚(Cheng-Shang Chang),林守德(Shou-De Lin),周承復(Cheng-Fu Chou) | |
dc.subject.keyword | 推薦系統,協同過濾,社群網路,信任網路,網路科學, | zh_TW |
dc.subject.keyword | Recommender System,Collaborative Filtering,Social Network,Trust Network,Network Science, | en |
dc.relation.page | 61 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2013-08-17 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 電機學研究所 | zh_TW |
顯示於系所單位: | 電機工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-102-1.pdf 目前未授權公開取用 | 2.87 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。