跳到主要內容

臺灣博碩士論文加值系統

(3.236.124.56) 您好!臺灣時間:2021/07/31 05:14
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

: 
twitterline
研究生:陳銘助
研究生(外文):Ming-ChuChen
論文名稱:利用使用者隱含資訊的新使用者喜好之預測系統
論文名稱(外文):Predict New Users’ Taste by Modeling Users’ Latent Features
指導教授:高宏宇高宏宇引用關係
指導教授(外文):Hung-Yu Kao
學位類別:碩士
校院名稱:國立成功大學
系所名稱:資訊工程學系碩博士班
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2012
畢業學年度:100
語文別:英文
論文頁數:42
中文關鍵詞:推薦系統協同過濾冷啟始問題
外文關鍵詞:Recommendation SystemCollaborative FilteringCold-Start Problem
相關次數:
  • 被引用被引用:0
  • 點閱點閱:165
  • 評分評分:
  • 下載下載:29
  • 收藏至我的研究室書目清單書目收藏:0
推薦系統近年來不管是在電子商務網站或是社群網路都蓬勃的發展。推薦系統中經常遇到的問題是當使用者第一次使用此推薦系統時,系統要如何在沒有使用者的喜好資料下幫新使用者找到其喜好並推薦,這類的問題便是所謂的Cold-Start Problem。這個研究的難度在於在推薦系統評分資料通常是非常稀疏的,必須要在稀疏的資料中找到喜好相似的使用者並決定出可以分辨這些使用者的問題來提問。而提問的問題的數量也不能太多,使用者通常沒有太多的耐心在於回答問題上。在此篇論文,我們提出了一個以透過分群使用者的隱含資訊來決定出最佳的問題的演算法Matrix Factorization K-Mean(MFK)來預測新使用者的喜好。藉由使用者在推薦系統中的評分資料來學習使用者的隱含特徵,透過這些隱含的資訊來決定出要問新使用者的問題。當新的使用者回答問題後,系統便可以運用新使用的回答來找到相似的使用者,並依照相似使用者的喜好來推薦使用者可能有興趣的物品。在實驗中,我們透過一個公開推薦系統評分資料來進行實驗分析。我們的方法比其他決定提問問題的基礎方法更為精確且有效,並能夠以較少的計算複雜度來接近現今最傑出的技術的實驗表現。
Recommendation system is popular in recent years. A key challenge in recommendation system is how to characterize new users taste effectively. The problem is generally known as the cold-start problem. New users judge the system by the ability to immediately provide what they are interesting. A general method for solving the cold-start problem is eliciting new users’ information by answering interview questions. In this paper, we present Matrix Factorization K-Means (MFK), a novel method to solve the problem of interview question construction. MFK first learns the user and item latent features by the observed rating data and then determine the best interview questions based on the clusters of latent features. We can find which group of users they are similar to after attain responses of the interview questions. Systems can indicate the new users’ taste according to their response on interview questions. In our experiments, we evaluate our methods in a public dataset for recommendation. The results show our method leads to a better performance compared with other baselines. Besides, the performance of our method is close to the state-of-the-art technique, while our method has a better computation complexity.
1. INTRODUCTION 1
1.1 Background 1
1.2 Motivation 3
1.3 Method Abstract 4
1.4 Paper organization 5
2. RELATED WORK 6
2.1 Collaborative Filtering 6
2.2 Cold-Start Collaborative Filtering 7
3. METHOD 9
3.1 Feature Extraction Model 10
3.1.1 Matrix Factorization 10
3.2 Question Selection Model 14
3.2.1 Latent Factor Clustering 14
3.2.2 Question Selection Strategies 15
3.2.3 Optimization 16
3.2.4 Computation Complexity 18
3.3 Prediction to New User 19
4. EXPERIMENTS 20
4.1 Dataset Description 20
4.2 Evaluation Metric 23
4.3 Experiments Design 23
4.4 Baseline Description 24
4.4.1 The Methods of Predicting Rating 24
4.4.2 The Methods of Selecting Interview Questions 25
4.5 Performance Comparisons 25
4.5.1 The Baselines on Predicting 26
4.5.2 The Baselines on Question Selection 27
4.5.3 State-of-the-Art Approaches 28
4.6 Real Case in Data Set 29
4.7 Compare with Warm-Start Setting 31
4.8 Impact of Model Parameters 32
4.8.1 Matrix Factorizations 34
4.8.2 Question Seed Set Size 36
4.8.3 Neighborhoods and Clusters 37
5. CONCLUSIONS & FUTURE WORK 39
6. REFERENCES 40
[1]Adomavicius, G. and A. Tuzhilin, Toward the Next Generation of Recommender Systems: A Survey of the State-of-the-Art and Possible Extensions, IEEE Trans. on Knowl. and Data Eng., vol. 17, pp. 734-749, 2005.
[2]Connor, M. and J. Herlocker, Clustering items for collaborative filtering, 2001.
[3]Gantner, Z., L. Drumond, C. Freudenthaler, S. Rendle, and L. Schmidt-Thieme, Learning Attribute-to-Feature Mappings for Cold-Start Recommendations, presented at the Proceedings of the 2010 IEEE International Conference on Data Mining, 2010.
[4]Golbandi, N., Y. Koren, and R. Lempel, Adaptive bootstrapping of recommender systems using decision trees, presented at the Proceedings of the fourth ACM international conference on Web search and data mining, Hong Kong, China, 2011.
[5]Golbandi, N., Y. Koren, and R. Lempel, On bootstrapping recommender systems, presented at the Proceedings of the 19th ACM international conference on Information and knowledge management, Toronto, ON, Canada, 2010.
[6]Goldberg, D., D. Nichols, B. M. Oki, and D. Terry, Using collaborative filtering to weave an information tapestry, Commun. ACM, vol. 35, pp. 61-70, 1992.
[7]Hofmann, T., Latent semantic models for collaborative filtering, ACM Trans. Inf. Syst., vol. 22, pp. 89-115, 2004.
[8]Koenigstein, N., G. Dror, and Y. Koren, Yahoo! music recommendations: modeling music ratings with temporal dynamics and item taxonomy, presented at the Proceedings of the fifth ACM conference on Recommender systems, Chicago, Illinois, USA, 2011.
[9]Koren, Y., R. Bell, and C. Volinsky, Matrix Factorization Techniques for Recommender Systems, Computer, vol. 42, pp. 30-37, 2009.
[10]Linden, G., B. Smith, and J. York, Amazon.com Recommendations: Item-to-Item Collaborative Filtering, IEEE Internet Computing, vol. 7, pp. 76-80, 2003.
[11]Ma, H., D. Zhou, C. Liu, M. R. Lyu, and I. King, Recommender systems with social regularization, presented at the Proceedings of the fourth ACM international conference on Web search and data mining, Hong Kong, China, 2011.
[12]Mooney, R. J. and L. Roy, Content-based book recommending using learning for text categorization, presented at the Proceedings of the fifth ACM conference on Digital libraries, San Antonio, Texas, United States, 2000.
[13]Park, S.-T. and W. Chu, Pairwise preference regression for cold-start recommendation, presented at the Proceedings of the third ACM conference on Recommender systems, New York, New York, USA, 2009.
[14]Pazzani, M. and D. Billsus, Learning and Revising User Profiles: The Identification ofInteresting Web Sites, Mach. Learn., vol. 27, pp. 313-331, 1997.
[15]Rashid, A. M., I. Albert, D. Cosley, S. K. Lam, S. M. McNee, J. A. Konstan, and J. Riedl, Getting to know you: learning new user preferences in recommender systems, presented at the Proceedings of the 7th international conference on Intelligent user interfaces, San Francisco, California, USA, 2002.
[16]Rashid, A. M., G. Karypis, and J. Riedl, Learning preferences of new users in recommender systems: an information theoretic approach, SIGKDD Explor. Newsl., vol. 10, pp. 90-100, 2008.
[17]Rendle, S., C. Freudenthaler, and L. Schmidt-Thieme, Factorizing personalized Markov chains for next-basket recommendation, presented at the Proceedings of the 19th international conference on World wide web, Raleigh, North Carolina, USA, 2010.
[18]Resnick, P., N. Iacovou, M. Suchak, P. Bergstrom, and J. Riedl, GroupLens: an open architecture for collaborative filtering of netnews, presented at the Proceedings of the 1994 ACM conference on Computer supported cooperative work, Chapel Hill, North Carolina, United States, 1994.
[19]Salakhutdinov, R. and A. Mnih. Probabilistic Matrix Factorization. Available: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.127.6198
[20]Sarwar, B., G. Karypis, J. Konstan, and J. Riedl, Item-based collaborative filtering recommendation algorithms, presented at the Proceedings of the 10th international conference on World Wide Web, Hong Kong, Hong Kong, 2001.
[21]Schein, A. I., A. Popescul, L. H. Ungar, and D. M. Pennock, Methods and metrics for cold-start recommendations, presented at the Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval, Tampere, Finland, 2002.
[22]Su, X. and T. M. Khoshgoftaar, A survey of collaborative filtering techniques, Adv. in Artif. Intell., vol. 2009, pp. 2-2, 2009.
[23]Su, X., T. M. Khoshgoftaar, and R. Greiner, A mixture imputation-boosted collaborative filter, in Proceedings of the 21st Conference of Florida Artificial Intelligence Research Society (FLAIRS¡¦08), 2008, pp. 312-317.
[24]Zhou, K., S.-H. Yang, and H. Zha, Functional matrix factorizations for cold-start recommendation, presented at the Proceedings of the 34th international ACM SIGIR conference on Research and development in Information Retrieval, Beijing, China, 2011.


連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊