請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/42491完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 鄭卜壬(Pu-Jen Cheng) | |
| dc.contributor.author | Yao-Chuan Wu | en |
| dc.contributor.author | 吳曜撰 | zh_TW |
| dc.date.accessioned | 2021-06-15T01:14:46Z | - |
| dc.date.available | 2009-07-31 | |
| dc.date.copyright | 2009-07-31 | |
| dc.date.issued | 2009 | |
| dc.date.submitted | 2009-07-29 | |
| dc.identifier.citation | [1] Breese, J. S., Heckerman, D., and Kadie, C. Empirical Analysis of Predictive Algorithms for Collaborative Filtering. In Proceedings of the 14th Annual Conference on Uncertainty in Artificial Interlligence, pp.43-52, 1998
[2] Shardanand, U., and Maes, P. Social Information Filtering: Algorithms for Automating ‘Word of Mouth’. In Proceedings of the Conference on Human Factors in Computing Systems (CHI95), pp.210-217, 1995 [3] Sarwar, B., Karypis, G., Konstan, J., and Riedl, J. Item-based Collaborative Filtering Recommendation Algorithms. In Proceedings of the 10th International World Wide Web Conference (WWW10), pp.285-295, 2001 [4] P. Resnick, N. Iacovou, M. Suchak, P. Bergstrom, and J. Riedl. Grouplens: An Open Architecture for Collaborative Filtering of Netnews. In Proceedings of the ACM Conference on Computer Supported Cooperative Work, pages 175—186, 1994 [5] J. L. Herlocker, J. A. Konstan, A. Borchers, and J. Riedl. An Algorithmic Framework for Performing Collaborative Filtering. In Proceedings of SIGIR, 1999. [6] R. Jin, J. Y. Chai, and L. Si. An Automatic Weighting Scheme for Collaborative Filtering. In Proceedings of SIGIR, 2004. [7] G.-R. Xue, C. Lin, Q. Yang, W. Xi, H.-J. Zeng, Y. Yu, and Z. Chen. Scalable Collaborative Filtering Using Cluster-based Smoothing. In Proceedings of SIGIR, 2005. [8] M. Deshpande and G. Karypis. Item-based top-N Recommendation Algorithms. In ACM Transactions on Information Systems (TOIS), 22(1):143–177, 2004. [9] G. Linden, B. Smith, and J. York. Amazon.com Recommendations: Item-to-Item Collaborative Filtering. In IEEE Internet Computing, pages 76–80, Jan/Feb 2003. [10] Hoffman, T. Collaborative Filtering via Gaussian Probabilistic Latent Semantic Analysis. In SIGIR. 2003 [11] Hofmann, T., and Puzicha, J. Latent class models for collaborative filtering. In Proceedings of International Joint Conference on Artificial Intelligence, 1999. [12] Si, L. and Jin, R. Flexible Mixture model for collaborative filtering. In Proceedings of the Twentieth International Conference on Machine Learning, 2003 [13] Dempster, A. P., Laird, N. M., and Rubin, D. B. Maximum likelihood from incomplete data via the EM algorithm. In Journal of Royal Statistical Society, B39:1-38, 1977. [14] U. Shardanand and P. Maes. Social Information Filtering: Algorithms for Automating Word of Mouth. In Proceedings of SIGCHI Conference on Human Factors in Computing Systems, 1995. [15] J. Canny. Collaborative Filtering with Privacy via Factor Analysis. In Proceedings of SIGIR, 2002. [16] A. Kohrs and B. Merialdo. Clustering for Collaborative Filtering Applications. In Proceedings of CIMCA, 1999. [17] L. H. Ungar and D. P. Foster. Clustering Methods for Collaborative Filtering. In Proceeding Workshop on Recommendation System at the 15th National Conf. on Artificial Intelligence, 1998. [18] http://www.grouplens.org/node/73 | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/42491 | - |
| dc.description.abstract | 以商品為基礎的協同過濾系統是一種有名且效能傑出的協同過濾系統。但以商品為基礎的協同過濾系統在遇到打愈多種不同分數的使用者的情況下效能會愈差；在遇到訓練資料不足的情況下效能也會愈差。為了解決此問題，我們提出了一個以評價為基礎的新方法。在此方法的第一步中，對於每一個使用者，將被評價為相同分數的商品群聚在一起。接著，對於每一種評價都為其建立一個預測模型。最後，我們計算出每一個模型之機率期望值，並且藉此來預測評價。藉由此種以評價為基礎的方法，預測之評價是利用每一個評價之模型產生，而非單純使用要被預測商品之相似商品來預測。我們的此種方法在MovieLens的一百萬筆評價資料集中表現得非常好。實驗結果也呈現出我們的方法比傳統的以商品為基礎的協同過濾的方法好，且有達到統計之顯著性。 | zh_TW |
| dc.description.abstract | Item-based collaborative filtering (CF) recommender system is one of famous and well-performed collaborative filtering recommender system. Item-based CF suffers from the problem of various ratings, while users give more different ratings. It also suffers from the problem of insufficient training data. In order to deal with these problems, we propose new methods called rate-based. In the first step, for each user, cluster items with the same rating. Then, build a model for each rating. Finally, make predictions of ratings by calculating the expectation value of models. Through our rate-based methods, predictions are made by utilizing the models of each rating rather than the neighbors of items which are going to be predicted. Our rate-based methods perform great on the million dataset of MovieLens. The experiment results show that our methods outperform the conventional item-based CF with statistically significant. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-15T01:14:46Z (GMT). No. of bitstreams: 1 ntu-98-R96922135-1.pdf: 2782965 bytes, checksum: e0a45f25b162f978ec604af3689096e2 (MD5) Previous issue date: 2009 | en |
| dc.description.tableofcontents | 摘要 ii
Abstract iii Acknowledgements iv Table of Contents v List of Figures viii Chapter 1 Introduction 1 1.1 Background and Motivation 1 1.2 Problems 5 1.2.1 Various ratings 5 1.2.2 Insufficient Training Data 7 1.3 Our Methods 9 1.4 Thesis Organization 10 Chapter 2 Related Work 11 2.1 Memory-Based Collaborative Filtering 11 2.1.1 User-Based Collaborative Filtering 11 2.1.2 Item-Based Collaborative Filtering 12 2.1.3 Similarity Measures 12 2.2 Model-Based Collaborative Filtering 13 2.2.1 Aspect Model 13 2.2.2 Flexible Mixture Model 14 Chapter 3 Methodology 16 3.1 Cluster Items 17 3.2 Generate the Models 17 3.2.1 Multi-Bernoulli Model – M1 18 3.2.2 Multinomial Model – M2 20 3.3 Background Model 22 3.3.1 Multi-Bernoulli Model – M1 22 3.3.2 Multinomial Model – M2 24 3.4 Mixture Model 25 3.5 Extension - Clustering Items in Each Model 27 3.6 Make Predictions 28 3.7 Discussion 29 Chapter 4 Experiments 32 4.1 Dataset 32 4.2 Evaluation Metrics 33 4.3 Experimental Results 34 4.3.1 Comparison of Our Methods to Item-Based CF 34 4.3.2 Effectiveness of Background Model 35 4.3.3 Effectiveness of Expectation Maximization 38 4.3.4 Effectiveness of the Number of Clusters 40 4.3.5 Effectiveness for Different Types of Users 47 4.4 Discussion 51 Chapter 5 Conclusion 53 5.1 Summary of Contributions 53 5.2 Future Work 54 Bibliography 55 | |
| dc.language.iso | en | |
| dc.subject | 模型 | zh_TW |
| dc.subject | 評價 | zh_TW |
| dc.subject | 協同過濾 | zh_TW |
| dc.subject | 推薦系統 | zh_TW |
| dc.subject | model | en |
| dc.subject | ratings | en |
| dc.subject | collaborative filtering | en |
| dc.subject | recommender system | en |
| dc.title | 以評價為基礎之協同過濾 | zh_TW |
| dc.title | Rate-Based Collaborative Filtering | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 97-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 陳信希(Hsin-Hsi Chen),張嘉惠(Chia-Hui Chang),曾新穆 | |
| dc.subject.keyword | 評價,協同過濾,推薦系統,模型, | zh_TW |
| dc.subject.keyword | ratings,collaborative filtering,recommender system,model, | en |
| dc.relation.page | 57 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2009-07-29 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 資訊工程學研究所 | zh_TW |
| 顯示於系所單位： | 資訊工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-98-1.pdf 未授權公開取用 | 2.72 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。