近年來由於網路的快速發展以及行動通訊的快速普及，使得我們在網路上能夠輕易地取得資料。然而隨著資料的傳遞速度加快，且資料量以不可計算的速度在增加的時候，使用者在搜尋所需資料時會被如此龐大的資訊量給淹沒，在沒有適當的方法來處理時，使用者會需要花上更多的時間去淘汰掉不必要的資料並從中篩選出可能需要的部分，使用者所需要的資料可能只佔了其中的一小部分，但是在這一來一往中使用者卻得花上大部分的時間去分辨這些所搜尋到的部分是否符合使用者需求，這樣的結果除了讓使用者徒增困擾以外最重要的是造成大量的時間浪費。
為了解決這個問題，本研究提出了以協同過濾法當中常使用的最近鄰居法與矩陣分解法來實作推薦系統，並以加入信任的因子以及將群體中較活躍的使用者當作參考對象的超級使用者來改進矩陣分解推薦系統，透過機械學習的方式來為使用者篩選大量的資訊，以找出更符合使用者需要的訊息來推薦給使用者。其中本研究除了對整體資料進行分析外，更是以使用者的評分次數來做分類，針對不同評分數的使用者來個別分析，並將結果與傳統的矩陣分解法推薦系統做比較，而在實驗中可以得知當有新加入的使用者時，本研究可以最有效的提供其推薦，並以此為本研究最大的貢獻。

The network and mobile communication develop very quickly in recent years. We could get the data easily online. However, the speed of data transformation is growing rapidly and the quantity of data is increasing. When user search for the data, they don’t know how to choose the suitable information. Without appropriate method, users will waste more time to eliminate from unnecessary data.
To solve this problem, this thesis proposes a method to build the recommendation system by matrix factorization. It combine trust relationships and super users to improve the efficiency of the matrix factorization recommendation system. Through the method of machine learning, it helps users screen the massive data and recommends the suitable information to users. In addition to the whole date, this thesis will analyze the different rating number users. And this thesis compares the result with traditional matrix factorization recommendation system. According to the experiment of this thesis, it discovers that when incoming users join the system. This research could provide the recommendation effectively, and it is the best contribute for this thesis.

論文審定書 i
摘要 ii
Abstract iii
目錄 iv
圖次 vi
表次 vii
第一章 緒論 1
1.1研究背景 1
1.2研究動機 3
1.3研究目的 4
第二章 文獻探討 5
2.1 信任(Trust) 5
2.2全域信任(Global Trust)與區域信任(Local Trust) 5
2.2.1全域信任 5
2.2.2 區域信任 5
2.3 結合信任的推薦系統 5
2.3.1 結合信任並以記憶為基底的協同過濾系統(Trust-aware Memory-based CF Systems) 6
2.3.2加入信任與權重(Trust-Aware Weighting) 6
2.4協同過濾演算法(Collaborative Filtering Algorithm) 7
2.4.1 User-based 7
2.4.2 user-based相似度計算 7
2.4.3 Item-based 7
2.4.4 Item-based相似度計算 8
2.4.5 最近鄰居法(K-Nearest Neighbor, KNN) 8
2.4.6 矩陣分解(Matrix Factorization) 9
2.4.7奇異值分解(Singular Value Decomposition ,SVD) 9
第三章 研究方法 13
3.1研究流程 14
3.2資料集 14
3.3最近鄰居法(K-Nearest Neighbor, KNN)標準系統實作 16
3.3.1相似度計算 16
3.3.2鄰居數K的選取 17
3.3.3.評估結果 17
3.4矩陣分解(Matrix Factorization)系統實作 17
3.5 結合信任與超級使用者的協同過濾法 19
3.5.1協同過濾演算法模型 20
3.5.2協同過濾演算法模型虛擬碼 22
3.6評估方法 25
第四章 實驗與結果 26
4.1資料集前處理 26
4.2最近鄰居法實作 26
4.3 SVD矩陣分解推薦系統 28
4.4結合信任與超級使用者的矩陣分解推薦系統實作 30
4.4.1使用者評分數目的選擇 30
4.4.2超級使用者的數量選擇 31
4.4.3與傳統矩陣分解比較 32
4.4.4不同評分次數使用者比較 33
4.4.5交叉驗證 35
第五章 結論與未來展望 44
5.1研究貢獻 44
5.2未來展望 44
參考文獻 46

[1] Eppler, Martin J., and Jeanne Mengis. "The concept of information overload: A review of literature from organization science, accounting, marketing, MIS, and related disciplines." The Information Society 20.5 (2004): 325-344.
[2] Koren, Yehuda, and Robert Bell. "Advances in collaborative filtering." Recommender Systems Handbook. Springer US, 2011. 145-186.
[3] Balabanović, Marko, and Yoav Shoham. "Fab: content-based, collaborative recommendation." Communications of the ACM 40.3 (1997): 66-72.
[4] Sarwar, Badrul, et al. "Item-based collaborative filtering recommendation algorithms." Proceedings of the 10th International Conference on World Wide Web. ACM, 2001.
[5] Wang, Jun, Arjen P. De Vries, and Marcel JT Reinders. "Unifying user-based and item-based collaborative filtering approaches by similarity fusion." Proceedings of the 29th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, 2006.
[6] Massa, Paolo, and Paolo Avesani. "Trust-aware recommender systems." Proceedings of the 2007 ACM Conference on Recommender Systems. ACM, 2007.
[7] Jamali, Mohsen, and Martin Ester. "A matrix factorization technique with trust propagation for recommendation in social networks." Proceedings of the fourth ACM conference on Recommender systems. ACM, 2010.
[8] Walter, Frank Edward, Stefano Battiston, and Frank Schweitzer. "A model of a trust-based recommendation system on a social network." Autonomous Agents and Multi-Agent Systems 16.1 (2008): 57-74..
[9] Guha, Ramanthan, et al. "Propagation of trust and distrust." Proceedings of the 13th International Conference on World Wide Web. ACM, 2004.
[10] Goldberg, David, et al. "Using collaborative filtering to weave an information tapestry." Communications of the ACM 35.12 (1992): 61-70.
[11] Ziegler, C-N., and Georg Lausen. "Spreading activation models for trust propagation." e-Technology, e-Commerce and e-Service, 2004. EEE'04. 2004 IEEE International Conference on. IEEE, 2004.
[12] Golbeck, Jennifer Ann. Computing and applying trust in web-based social networks. Diss. 2005.
[13] Jamali, Mohsen, and Martin Ester. "Trustwalker: a random walk model for combining trust-based and item-based recommendation." Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2009.
[14] Papagelis, Manos, and Dimitris Plexousakis. "Qualitative analysis of user-based and item-based prediction algorithms for recommendation agents." Engineering Applications of Artificial Intelligence 18.7 (2005): 781-789.
[15] Kim, Heung-Nam, et al. "Collaborative filtering based on collaborative tagging for enhancing the quality of recommendation." Electronic Commerce Research and Applications 9.1 (2010): 73-83.
[16] Sieg, Ahu, Bamshad Mobasher, and Robin Burke. "Improving the effectiveness of collaborative recommendation with ontology-based user profiles." Proceedings of the 1st International Workshop on Information Heterogeneity and Fusion in Recommender Systems. ACM, 2010.
[17] Guo, Guibing, Jie Zhang, and Neil Yorke-Smith. "TrustSVD: Collaborative Filtering with Both the Explicit and Implicit Influence of User Trust and of Item Ratings." AAAI, 2015.
[18] Ma, Hao, Michael R. Lyu, and Irwin King. "Learning to recommend with trust and distrust relationships." Proceedings of the Third ACM Conference on Recommender Systems. ACM, 2009.
[19] Yang, Bo, et al. "Social collaborative filtering by trust." IEEE Transactions on Pattern Analysis and Machine Intelligence (2016).
[20] Koren, Yehuda. "Factorization meets the neighborhood: a multifaceted collaborative filtering model." Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2008.
[21] Wu, Mingrui. "Collaborative filtering via ensembles of matrix factorizations." Proceedings of KDD Cup and Workshop. Vol. 2007. 2007.
[22] Su, Xiaoyuan, and Taghi M. Khoshgoftaar. "A survey of collaborative filtering techniques." Advances in Artificial Intelligence 2009 (2009): 4.
[23] Rendle, Steffen, et al. "BPR: Bayesian personalized ranking from implicit feedback." Proceedings of the Twenty-fifth Conference on Uncertainty in Artificial Intelligence. AUAI Press, 2009.
[24] Jahrer, Michael, Andreas Töscher, and Robert Legenstein. "Combining predictions for accurate recommender systems." Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2010.
[25] Koren, Yehuda, Robert Bell, and Chris Volinsky. "Matrix factorization techniques for recommender systems." Computer 42.8 (2009).