研究生: |
陳泓瑋 Hung-Wei Chen |
---|---|
論文名稱: |
內容導向電影推薦系統結合類神經網路之特徵抽取 Fully Content-based Movie Recommender System with Feature Extraction Using Neural Network |
指導教授: |
吳怡樂
Yi-Leh Wu |
口試委員: |
陳建中
none 唐政元 none 閻立剛 none |
學位類別: |
碩士 Master |
系所名稱: |
電資學院 - 資訊工程系 Department of Computer Science and Information Engineering |
論文出版年: | 2016 |
畢業學年度: | 104 |
語文別: | 英文 |
論文頁數: | 29 |
中文關鍵詞: | 推薦系統 、內容導向 、類神經網路 、特徵抽取 |
外文關鍵詞: | Recommender system, content-based, neural network, feature extraction |
相關次數: | 點閱:279 下載:0 |
分享至: |
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
近年來電影工業發展蓬勃,每年都有上百部的電影推陳出新,而一般人一年看的電影可能才十至二十部。使用者不僅無法快速吸收這麼大量的資訊,想從中挑選出中意的電影更是難上加難。因此,電影推薦作為研究主題越來越受到矚目。在電影推薦系統中,處理新電影是以內容導向的電影推薦系統為主流,因其不使用使用者資訊,只用電影內容的資訊作為輸入的特性,使其不管面對新舊電影都可以保持一樣的表現。
本論文提出了純內容導向電影推薦系統,將電影的相關資訊如導演、演員、類型…等等做為輸入來推薦電影。本系統利用類神經網路對電影的內容資訊進行特徵抽取,用抽取出的向量計算電影間的相似度,並以此為基準進行推薦。我們使用Movielens-20M資料集來測試我們的系統,實驗結果證明了使用者在選擇電影時,確實會考量電影的相關資訊。
In recent year, movie industry is getting prosper. There are hundreds of movie released every year. However, it is difficult to notice the releasing of every movie, not to mention actually seeing it. Therefore, movie recommender system has become more and more popular as a research topic. Among a variety of movie recommender systems, content-based methods always ring a bell when it comes to recommending new movie. Content-based method use content of movie as input so that it does not suffer from “cold-start” problem.
In this paper, we propose the Fully Content-based Movie Recommender System (FCMR) to recommend movies to users. The proposed method trains a neural network model, Word2Vec CBOW, with content information (e.g., cast, crew, etc.) as the training data to obtain vector form features of each elements, and then take advantage of the linear relationship of learned feature to calculate the similarity between each movie. In the end, the proposed FCMR recommends movies based on the similarity. The experiments are conducted on a massive real world dataset, and the intuition behind our proposed method has been proven by the experiment results.
[1] Koren, Y., Bell, R., & Volinsky, C. (2009). Matrix factorization techniques for recommender systems. Computer, (8), 30-37, 2009.
[2] Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781, 2013.
[3] Herlocker, J. L., Konstan, J. A., Borchers, A., & Riedl, J. (1999, August). An algorithmic framework for performing collaborative filtering. In Proceedings of the 22nd annual international ACM SIGIR conference on Research and development in information retrieval (pp. 230-237), 1999.
[4] Sarwar, B., Karypis, G., Konstan, J., & Riedl, J. (2001, April). Item-based collaborative filtering recommendation algorithms. In Proceedings of the 10th international conference on World Wide Web (pp. 285-295), 2001.
[5] Herlocker, J. L., Konstan, J. A., & Riedl, J. (2000, December). Explaining collaborative filtering recommendations. In Proceedings of the 2000 ACM conference on Computer supported cooperative work (pp. 241-250), 2000.
[6] Ono, C., Kurokawa, M., Motomura, Y., & Asoh, H. (2007). A context-aware movie preference model using a Bayesian network for recommendation and promotion. In User Modeling 2007 (pp. 247-257), 2007.
[7] Lee, Y. S., Pham, X. H., Trung, D. N., Jung, J. J., & Nguyen, H. T. (2013). Social Context-Based Movie Recommendation: A Case Study on MyMovieHistory. In Context-Aware Systems and Applications (pp. 339-348), 2013.
[8] Said, A., Berkovsky, S., & De Luca, E. W. (2010, September). Putting things in context: Challenge on context-aware movie recommendation. In Proceedings of the Workshop on Context-Aware Movie Recommendation (pp. 2-6), 2010.
[9] Debnath, S., Ganguly, N., & Mitra, P. (2008, April). Feature weighting in content based recommendation system using social network analysis. In Proceedings of the 17th international conference on World Wide Web (pp. 1041-1042), 2008.
[10] Shi, Y., Larson, M., & Hanjalic, A. (2010, September). Mining mood-specific movie similarity with matrix factorization for context-aware recommendation. In Proceedings of the workshop on context-aware movie recommendation (pp. 34-40), 2010.
[11] Lehinevych, T., Kokkinis-Ntrenis, N., Siantikos, G., Dogruoz, A. S., Giannakopoulos, T., & Konstantopoulos, S. (2014, November). Discovering similarities for content-based recommendation and browsing in multimedia collections. In Signal-Image Technology and Internet-Based Systems (SITIS), 2014 Tenth International Conference on (pp. 237-243), 2014.
[12] Diao, Q., Qiu, M., Wu, C. Y., MBla, A. J., Jiang, J., & Wang, C. (2014, August). Jointly modeling aspects, ratings and sentiments for movie recommendation (jmars). In Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining (pp. 193-202), 2014.
[13] Uluyagmur, M., Cataltepe, Z., & Tayfur, E. (2012). Content-based movie recommendation using different feature sets. In Proceedings of the World Congress on Engineering and Computer Science (Vol. 1, pp. 17-24), 2012.
[14] Lekakos, G., & Caravelas, P. (2008). A hybrid approach for movie recommendation. Multimedia tools and applications, 36(1-2), 55-70, 2008.
[15] De Campos, L. M., Fernández-Luna, J. M., Huete, J. F., & Rueda-Morales, M. A. (2010). Combining content-based and collaborative recommendations: A hybrid approach based on Bayesian networks. International Journal of Approximate Reasoning, 51(7), 785-799, 2010.
[16] Porteous, I., Asuncion, A. U., & Welling, M. (2010, July). Bayesian Matrix Factorization with Side Information and Dirichlet Process Mixtures, 2010.
[17] De Campos, L. M., Fernández-Luna, J. M., Huete, J. F., & Rueda-Morales, M. A. (2010). Combining content-based and collaborative recommendations: A hybrid approach based on Bayesian networks. International Journal of Approximate Reasoning, 51(7), 785-799, 2010.
[18] Shan, H., & Banerjee, A. (2010, December). Generalized probabilistic matrix factorizations for collaborative filtering. In Data Mining (ICDM), 2010 IEEE 10th International Conference on (pp. 1025-1030), 2010.
[19] Park, S., Kim, Y. D., & Choi, S. (2013, August). Hierarchical Bayesian Matrix Factorization with Side Information, 2013.
[20] Wang, H., Wang, N., & Yeung, D. Y. (2015, August). Collaborative deep learning for recommender systems. In Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 1235-1244), 2015.
[21] Van den Oord, A., Dieleman, S., & Schrauwen, B. (2013). Deep content-based music recommendation. In Advances in Neural Information Processing Systems (pp. 2643-2651), 2013.
[22] Elkahky, A. M., Song, Y., & He, X. (2015, May). A multi-view deep learning approach for cross domain user modeling in recommendation systems. In Proceedings of the 24th International Conference on World Wide Web (pp. 278-288), 2015.
[23] Movie dataset, http://grouplens.org/datasets/movielens/, referenced on April 28th, 2016.
[24] Word2Vec implementation in C https://code.google.com/archive/p/word2vec/ referenced on April 16th, 2016.
[25] Word2Vec implementation in Java, https://github.com/medallia/Word2VecJava referenced on April 16th, 2016.