跳到主要內容

臺灣博碩士論文加值系統

(44.220.255.141) 您好!臺灣時間:2024/11/15 02:26
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

我願授權國圖
: 
twitterline
研究生:馮雅婷
研究生(外文):Feng, Ya-Ting
論文名稱:基於調整使用者興趣與推薦多樣性之線上新聞推薦
論文名稱(外文):Online News Recommendation based on Adjustment of User Interest and Recommendation Diversity
指導教授:劉敦仁劉敦仁引用關係
指導教授(外文):Liu, Duen-Ren
口試委員:周世傑劉敦仁羅濟群陳安斌
口試委員(外文):Chou, Shih-ChiehLiu, Duen-RenLo, Chi-ChunChen, An-Pin
口試日期:2019-07-04
學位類別:碩士
校院名稱:國立交通大學
系所名稱:資訊管理研究所
學門:電算機學門
學類:電算機一般學類
論文種類:學術論文
論文出版年:2019
畢業學年度:107
語文別:英文
論文頁數:38
中文關鍵詞:新聞推薦矩陣分解文章標註隱含主題模型協同主題模型文章主題推薦多樣性
外文關鍵詞:News Recommender SystemMatrix FactorizationLatent Dirichlet AllocationCollaborative Topic ModelArticle TitleArticle TagRecommendation Diversity
相關次數:
  • 被引用被引用:0
  • 點閱點閱:260
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
隨著網路蓬勃發展,使用者難以在數百萬計的資料中找到適合的資訊,此時,推薦系統能有效幫助使用者過濾資訊。近年來,隨著推薦系統的演進,使用者開始注重個人化的推薦清單,傳統追求準確率的方法已無法滿足使用者的需求,多樣化的推薦更能幫助使用者挖掘隱含興趣,改善資料稀疏性及冷啟動等問題。
本研究應用於新聞推薦上,為優化準確率及多樣性,結合協同主題模型及協同過濾模型,並且避免推薦過於發散,使用基於分群的推薦多樣性來改善推薦效果。除此之外,本研究提出了調整多樣性參數之方法,有效針對冷啟動使用者,即瀏覽紀錄稀少的使用者,推薦多樣化之清單,而對於瀏覽紀錄較多的使用者,也能維持一定準確率。本研究也實作於線上實驗,針對使用者即時瀏覽紀錄,基於LDA相似度即時更新推薦清單及喜好分數,最終將以點擊率作為線上實驗的評估依據。
Owing to the tremendous growth in the amount of information, it becomes more difficult for users to find relevant content in millions of articles. In order to solve this dilemma, personalized recommendations have been widely used to help users find interesting items and maintain high accuracy.
However, it still remains difficulties – the cold-start and data sparsity problems. Furthermore, users’ interests are changed frequently, traditional Collaborative Filtering and Content-based Filtering recommendations methods can’t meet the needs of users anymore. In recent research, diversified recommendation is believed to help alleviate the cold start problem and arouse the interests of users.
In order to balance accuracy and diversity, we propose a hybrid recommender model (HCTM), combining Collaborative Topic Model (CTM) and similarity-based CF model. To avoid divergence, we propose a novel recommendation which integrate HCTM and dynamic cluster-based diverse analysis. According to the amount of user’s browsing, we adjust a numeric setting for individual user, which we regarded as user diversity parameter. The online experiments and evaluation are conducted on the online news website NiusNews. We also consider users’ online interests, LDA-based online interest, and update our recommendation list. The experiment results show that the proposed approach can effectively improve the CTR of online recommendation.
摘 要 i
ABSTRACT ii
致謝 iii
List of Tables vi
List of Figures vii
1 Introduction 1
1.1 Background 1
1.2 Motivation 2
1.3 Objectives 3
2 Related Work 5
2.1 Recommendation System 5
2.1.1 Memory-based CF 6
2.1.2 Model-based CF 6
2.1.3 Hybrid CF 7
2.2 Collaborative Topic Model 7
2.2.1 Matrix Factorization (MF) 7
2.2.3 Latent Topic Modeling 8
2.2.3 Collaborative Topic Model 9
2.3 Diverse Recommendation 9
2.4 Online Recommendation 10
3 Proposed Approach 11
3.1 Overview 11
3.2 Data-Preprocessing 13
3.2.1 Latent Topic Model for News 13
3.3 Offline User Preferences Analysis 13
3.3.1 Collaborative Topic Model (CTM) 13
3.3.2 Similarity-based CF Model 15
3.3.3 User Diversity 16
3.4 Online Recommendation 17
3.4.1 Cluster-based Diverse Recommendation 18
4 Experiment and Evaluation 21
4.1.1 Evaluation Metrics 21
4.1 Dataset and Experiment Setup 22
4.1.2 The Compared Methods in Offline and Online Recommendation 23
4.2 Model Evaluation and Parameter Setting 25
4.2.1 Evaluation of Parameter for CTM 25
4.2.2 Evaluation the Parameters for Title-based CF Model 26
4.2.3 Evaluation the Parameters for Tag-based CF Model 27
4.2.4 Evaluation the Parameters for HCTM Model 28
4.2.5 Evaluation the Parameters for HCTM-CD for Recommendation 29
4.2.6 Evaluation the Parameters for HCTM-CDD for Recommendation 30
4.3 Online Evaluation 31
5 Conclusion and Future Work 34
6 Reference 35
[1] S. Abbar, S. Amer-Yahia, P. Indyk, S. Mahabadi, Real-time recommendation of diverse related articles, Proceedings of the 22nd international conference on World Wide Web, 2013, pp. 1-12.
[2] G. Adomavicius, Y. Kwon, Maximizing aggregate recommendation diversity: A graph-theoretic approach, Proc. of the 1st International Workshop on Novelty and Diversity in Recommender Systems (DiveRS 2011), 2011, pp. 3-10.
[3] T. Aytekin, M.Ö. Karakaya, Clustering-based diversity improvement in top-N recommendation, Journal of Intelligent Information Systems, 42 (1), 2014, pp. 1-18.
[4] R. Baeza-Yates, B. Ribeiro-Neto, Modern information retrieval, ACM press New York, 1999.
[5] M. Balabanović, Y. Shoham, Fab: content-based, collaborative recommendation, Communications of the ACM, 40 (3), 1997, pp. 66-72.
[6] L. Baltrunas, B. Ludwig, F. Ricci, Matrix factorization techniques for context aware recommendation, Proceedings of the fifth ACM conference on Recommender systems, 2011, pp. 301-304.
[7] S. Bansal, C. Gupta, A. Arora, User tweets based genre prediction and movie recommendation using LSI and SVD, Contemporary Computing (IC3), 2016 Ninth International Conference on, 2016, pp. 1-6.
[8] D.M. Blei, A.Y. Ng, M.I. Jordan, Latent dirichlet allocation, Journal of machine Learning research, 3 (Jan), 2003, pp. 993-1022.
[9] J.G. Carbonell, J. Goldstein, The Use of MMR and Diversity-Based Reranking for Reodering Documents and Producing Summaries, 1998, pp.
[10] O. Celma, Music recommendation, in: Music recommendation and discovery, Springer, 2010, pp. 43-85.
[11] F. Eskandanian, B. Mobasher, R. Burke, A Clustering Approach for Personalizing Diversity in Collaborative Recommender Systems, Proceedings of the 25th Conference on User Modeling, Adaptation and Personalization, 2017, pp. 280-284.
[12] A. Ghabayen, S.A. Noah, Exploiting social tags to overcome cold start recommendation problem, Journal of Computer Science, 10 (7), 2014, pp. 1166.
[13] A. Gogna, A. Majumdar, Balancing accuracy and diversity in recommendations using matrix completion framework, Knowledge-Based Systems, 125, 2017, pp. 83-95.
[14] C. Huang, J. Yin, Effective association clusters filtering to cold-start recommendations, 2010 Seventh International Conference on Fuzzy Systems and Knowledge Discovery, 2010, pp. 2461-2464.
[15] M. Jamali, M. Ester, A matrix factorization technique with trust propagation for recommendation in social networks, Proceedings of the fourth ACM conference on Recommender systems, 2010, pp. 135-142.
[16] C. Ju, C. Xu, A new collaborative recommendation approach based on users clustering using artificial bee colony algorithm, The Scientific World Journal, 2013, 2013, pp.
[17] H. Khotimah, T. Djatna, Y. Nurhadryani, Tourism recommendation based on vector space model using composite social media extraction, Advanced Computer Science and Information Systems (ICACSIS), 2014 International Conference on, 2014, pp. 303-308.
[18] M. Kompan, M. Bieliková, Content-based news recommendation, International conference on electronic commerce and web technologies, 2010, pp. 61-72.
[19] M.R. Koochi, A.R.C. Hussin, H.M. Dahlan, Improving recommendation diversity using tensor decomposition and clustering approaches, Information and Communication Technologies (WICT), 2014 Fourth World Congress on, 2014, pp. 240-245.
[20] Y. Koren, R. Bell, C. Volinsky, Matrix factorization techniques for recommender systems, Computer, 42 (8), 2009, pp.
[21] Z.E. Koupaei, M. Khayyambashi, Improving Recommendation Diversity by Classifying Users Based on Demographic Information, IJCCER, 3 (4), 2015, pp. 68-74.
[22] C.-H. Lai, D.-R. Liu, C.-S. Lin, Novel personal and group-based trust models in collaborative filtering for document recommendation, Information Sciences, 239, 2013, pp. 31-49.
[23] X. Li, T. Murata, Multidimensional clustering based collaborative filtering approach for diversified recommendation, Computer Science & Education (ICCSE), 2012 7th International Conference on, 2012, pp. 905-910.
[24] Y. Li, M. Yang, Z.M. Zhang, Scientific articles recommendation, Proceedings of the 22nd ACM international conference on Conference on information & knowledge management, 2013, pp. 1147-1156.
[25] Y.-H. Liao, Online News Recommendation based on Collaborative Topic Modeling and Recommendation Diversity, in, National Chiao Tung University, 2018, pp. 1-47.
[26] Y.-C. Lin, 以使用者喜好多樣性及跨領域分析為基礎之線上商品推薦方法, 交通大學資訊管理研究所學位論文, 2016, pp. 1-40.
[27] D.-R. Liu, C.-H. Lai, W.-J. Lee, A hybrid of sequential rules and collaborative filtering for product recommendation, Information Sciences, 179 (20), 2009, pp. 3505-3519.
[28] K. Niemann, M. Wolpers, A new collaborative filtering approach for increasing the aggregate diversity of recommender systems, Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining, 2013, pp. 955-963.
[29] M.-H. Park, J.-H. Hong, S.-B. Cho, Location-based recommendation system using bayesian user’s preference model in mobile devices, International Conference on Ubiquitous Intelligence and Computing, 2007, pp. 1130-1139.
[30] M.J. Pazzani, D. Billsus, Content-based recommendation systems, in: The adaptive web, Springer, 2007, pp. 325-341.
[31] D.M. Pennock, E. Horvitz, S. Lawrence, C.L. Giles, Collaborative filtering by personality diagnosis: A hybrid memory-and model-based approach, Proceedings of the Sixteenth conference on Uncertainty in artificial intelligence, 2000, pp. 473-480.
[32] R. Pálovics, A.A. Benczúr, L. Kocsis, T. Kiss, E. Frigó, Exploiting temporal influence in online recommendation, Proceedings of the 8th ACM Conference on Recommender systems, 2014, pp. 273-280.
[33] V. Pouli, J.S. Baras, A. Arvanitis, Increasing recommendation accuracy and diversity via social networks hyperbolic embedding, Consumer Communications and Networking Conference (CCNC), 2014 IEEE 11th, 2014, pp. 225-232.
[34] W. Premchaiswadi, P. Poompuang, N. Jongswat, N. Premchaiswadi, Enhancing Diversity-Accuracy Technique on User-Based Top-N Recommendation Algorithms, Computer Software and Applications Conference Workshops (COMPSACW), 2013 IEEE 37th Annual, 2013, pp. 403-408.
[35] S. Ren, S. Gao, J. Liao, J. Guo, Improving cross-domain recommendation through probabilistic cluster-level latent factor model, Twenty-Ninth AAAI Conference on Artificial Intelligence, 2015, pp.
[36] R.L. Rosa, D.Z. Rodríguez, G. Bressan, Music recommendation system based on user's sentiments extracted from social networks, 2015 IEEE International Conference on Consumer Electronics (ICCE), 2015, pp. 383-384.
[37] S. Singh, S. Bag, M. Jenamani, Relative similarity based approach for improving aggregate recommendation diversity, India Conference (INDICON), 2015 Annual IEEE, 2015, pp. 1-6.
[38] H. Sobhanam, A. Mariappan, Addressing cold start problem in recommender systems using association rules and clustering technique, Computer Communication and Informatics (ICCCI), 2013 International Conference on, 2013, pp. 1-5.
[39] C. Wang, D.M. Blei, Collaborative topic modeling for recommending scientific articles, Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining, 2011, pp. 448-456.
[40] J. Wang, J. Yin, Combining user-based and item-based collaborative filtering techniques to improve recommendation diversity, Biomedical Engineering and Informatics (BMEI), 2013 6th International Conference on, 2013, pp. 661-665.
[41] Q. Wu, S. Liu, C. Miao, Modeling uncertainty driven curiosity for social recommendation, Proceedings of the International Conference on Web Intelligence, 2017, pp. 790-798.
[42] Q. Wu, S. Liu, C. Miao, Y. Liu, C. Leung, A social curiosity inspired recommendation model to improve precision, coverage and diversity, Web Intelligence (WI), 2016 IEEE/WIC/ACM International Conference on, 2016, pp. 240-247.
[43] W. Wu, J. Zhao, C. Zhang, F. Meng, Z. Zhang, Y. Zhang, Q. Sun, Improving performance of tensor-based context-aware recommenders using Bias Tensor Factorization with context feature auto-encoding, Knowledge-Based Systems, 128, 2017, pp. 71-77.
[44] Z.-K. Zhang, C. Liu, Y.-C. Zhang, T. Zhou, Solving the cold-start problem in recommender systems with social tags, EPL (Europhysics Letters), 92 (2), 2010, pp. 28002.
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