研究生: |
李育維 Yu-Wei Lee |
---|---|
論文名稱: |
依收視群喜好推薦節目之互動電視系統 A Group Profile Based Program Recommender for Interactive TV |
指導教授: |
陳建中
Jiann-Jone Chen |
口試委員: |
陳永昌
Yung-Chang Chen 郭天穎 Tien-Ying Kuo 許新添 Hsin-Teng Hsu 陳志明 Chih-Ming Chen |
學位類別: |
碩士 Master |
系所名稱: |
電資學院 - 電機工程系 Department of Electrical Engineering |
論文出版年: | 2012 |
畢業學年度: | 100 |
語文別: | 中文 |
論文頁數: | 88 |
中文關鍵詞: | 人機介面 、社會群體 、推薦系統 、類神經網路 |
外文關鍵詞: | Human-Machine Interface, Social Group, Recommender System, Neural Network |
相關次數: | 點閱:284 下載:5 |
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 |
隨著資訊科技的進步,多媒體內容資訊量已急遽增加,如何在大量的資料中讓使用者快速找到真正想要或者感興趣的資料,推薦系統(Recommender System)將扮演重要角色。例如Amazon, Barnes&Noble等。過去相關研究大多基於個人喜好所設計,作法是記錄個人之行為與喜好模式,推薦程序依據使用者喜好模式估計喜好程度。應用於電視節目的推薦系統,例如家庭中收看電視時常為多人同時觀賞,個人化推薦系統並無法滿足此應用情境,因需考慮群觀眾的喜好特徵。過去在群體推薦系統中常用的作法是將群體中所有成員對物件的喜好合併後代表群體對物件的評比,這種作法忽略了群體成員的人格特質與成員間互動模式,因此產生的評比結果將無法反映出群體對物件的實際喜好。近來智慧電視朝人性化與互動化發展,如何整合智慧電視與多媒體服務以改善人們在使用上的便利性,將是未來研究重點。本論文提出一應用於互動電視之可適性推薦系統,利用智慧電視搭載之人機介面辨識使用者身分,分別針對個人使用者及群體使用者進行不同之推薦模組,前者利用混合式推薦演算法,結合內容導向式演算法及協合過濾式演算法兩者的優點,預測出個人對節目的評比,後者利用人工類神經網路模擬成員間相互影響現象,輸入個人對節目評比後,透過神經網路加權整合後預測出群體對節目的評比。在長期收看電視的情境下,個人化推薦模組透過更新演算法,利用個人觀看歷史記錄逐次更新使用者喜好,讓系統能夠更人性化地了解使用者喜好。群體推薦模組則是利用群體觀看歷史記錄,透過誤差倒傳遞演算法訓練出實際成員互動主導模式,能夠滿足所有成員之需求。經由人機介面所蒐集多使用者之反饋訊息,逐次調整相關參數,使本推薦系統達到可適性的目的。
Personalized recommender systems has been developed for applications such as online bookstore Barnes&Noble, online shopping mall Amazon, and multimedia programs. They are developed based on recorded user preferences to estimate user ratings on new items/stuffs. To recommend TV programs or movies, it has to perform recommendation for group users. By simply merging preferences of group users, it can act as a single user for recommendation. However, this approach ignores individual preferences and user dominance in interaction, which cannot reflect practical group users’ preferences. We proposed to estimate inter-user dominance factor through the neural network algorithm, based on practical group user rating records. In addition, both content-based and user-based collaborative filtering algorithms are adopted based on the inter-user dominant factors to predict group users’ preference for program recommendation. The proposed adaptive program recommender based on group user profiles is evaluated from practical experiments on Movielens user rating databases. In addition, an active face recognition module has been integrated with the recommender system to provide touchless and user-friendly interface for a family TV program recommendation prototype. Experiments showed that the proposed method can achieve higher accuracy in recommending video programs for group users, in additional to user-friendly recommendation function.
[1] 三星電子http://www.samsung.com
[2] G.C. Homans, “The human group,” Transaction Publishers, New York: Harcourt, Brace, & World, Jan. 1991.
[3] A. P. Hare, “Handbook of small group research,” Free Pr; 2nd ed., Nov. 1976.
[4] H. Bonner, “Group dynamics: principles and applications,” New York: Ronald Press Company, 1959.
[5] D. Cartwright and A. Zander, “Group dynamics: research and theory,” New York: Harper & Row, 3rd Ed., 1968.
[6] E. P. Hollander, “Principles and methods of social psychology,” New York: Oxford University Press, 1971.
[7] E. P. Torrance, “Some consequences of power difference on decision making in permanent and temporary three-man groups,” In Research Studies 22, State College of Washington, pp130–140, 1954.
[8] M. Balabanovic and Y. Shoham. Fab:Content-based, collaborative recommendation. Communications of the ACM, 40(3):66–72, 1997.
[9] Ben J. Schafer, Joseph A. Konstan, John Riedl, “E-Commerce Recommendation Applications,” Data Mining and Knowledge Discovery, Vol. 5, No. 1-2. , pp. 115-153, January 2001
[10] M. J. Pazzani and D. Billsus, “Content-based recommendation systems,” Lecture Notes in Computer and Information Science, pp.325-341, 2007.
[11] Recommender system handbook, Publisher: Springer; 1st Edition. edition ,October 28, 2010.
[12] T. Hofmann, “Collaborative filtering via Gaussian probabilistic latent semantic analysis,” Int. ACM SIGIR conf. Research and Development in Information Retrieval, pp.259-266, 2003.
[13] C. Basu, H. Hirsh, W.Cohen, “Recommendation as Classification:Using social and content-based information in recommendation,” In Recommender System Workshop’98.pp.11-15,1998.
[14] J.A. Konstan, B.N. Miller, D. Maltz, J.L. Herlocker, L.R. Gordon, and J. Riedl, “GroupLens: applying collaborative filtering to usenet news,” Communications of the ACM, pp.77-87, 1997.
[15] W. Hill, L. Stead, M. Rosenstein, and G. Furnas, “Recommending and evaluating choices in a virtual community of use,” in Proc. of SIGCHI conf. on Human factors in computing systems, pp.194-201, 1995.
[16] U. Shardanand, and P. Maes, “Social information filtering: algorithms for automating ‘word of mouth’,” in Procs. of SIGCHI conf. on Human factors in computing systems, pp.194–201, 1995.
[17] A. Paterek, “Improving regularized singular value decomposition for collaborative filtering,” In Proc. of the KDD Cup and Workshop, 2007.
[18] G. Tak’acs, I. Pil’aszy, B. N’emeth, and D. Tikk, “Scalable collaborative filtering approaches for large recommender systems,” Jour. of Machine Learning Research, vol.10, pp.623–656, 2009.
[19] M. Grcar, B. Fortuna, D. Mladenic, and M. Grobelnik, “k-NN versus SVM in the collaborative filtering framework. Data Science and Classification,” In Data Science and Classification, pp.251–260, May 2006.
[20] Cane W.-k. Leung, Stephen C.-f. Chan, and F.-l. Chung, “Applying cross-level association rule mining to cold-start recommendations,” IEEE International conf. Web Intelligence and Intelligent Agent Technology, 2007.
[21] J. Wang, A. P. de Vries, and M. J.T. Reinders, “Unifying user-based and item-based collaborative filtering approaches by similarity fusion”, in Proc. of ACM SIGIR Conference on Information Retrieval, pp.501-508, 2006.
[22] K. Park, J. Choi, and D. Lee, “A single-scaled hybrid filtering method for IPTV program recommendation,” Int. J. Circuits, Systems Signal Processing, vol.4, pp.161-168, 2010.
[23] R. Burke, “Hybrid recommender systems: Survey and experiments,” User Modeling and User-Adapted Interaction, vol.12, pp.331-370, Nov. 2002.
[24] J. Masthoff, “Group modeling: selecting a sequence of television items to suit a group of viewers,” User Model and User-Adapted Interaction, vol.14, pp.37–85, 2004.
[25] J. F. McCarthy, and T. D. Anagnost, “MusicFX: An arbiter of group preferences for computer supported collaborative workouts,” In Proc. of ACM conf. on Computer supported cooperative work, pp.363-372, 1998.
[26] M. O’Connor, D. Cosley, J. Konstan, and J. Riedl, “PolyLens: A recommender system ofr groups fo users,” In Proc. of European conf. on Computer-Supported Cooperative Work, pp.199-218, 2001.
[27] F. Rosenblatt, “The perceptron: a probabilistic model for information storage and organization in the brain,” Psychological Review, vol.65 Issue 6, pp.386-408, 1958.
[28] 葉怡成, 「類神經網路模式應用與實作」,儒林圖書公司, 民88.
[29] B.Sarwar, G.Karypis, J.Konstan,and J.Riedl, “Item-Based Collaborative Filtering Recommendation Algorithm,” In Proceedings of the 10th international conference on World Wide Web, pp.285-295, Hong-Kong, 2001.
[30] 張睿哲, 「應用類神經網路於群體互動之協合過濾式群體推薦系統」,國立臺灣科技大學碩士學位論文, 民100.
[31] http://movielens.umn.edu.
[32] Yen-Liang Chen , Li-Chen Cheng , Ching-Nan Chuang , “A group recommendation system with consideration of interactions among group members, ” Expert Systems with Applications:An International Jounal,v.34n.3,p.2082-2090,April,2008
[33] Y. Y. YAO, ”Measuring retrieval effectiveness based on user preference of documents,” Journal of the American Society for Information Science, pp.133-145,1995.
[34] K.H. Lin,and Y.S Chiu,and J.S. Chen ”An adaptive correlation-based group recommendation system” Intelligent Symposium on Intelligent Signal Processing and Communication System(ISPACS) December 7-9,2011.
[35] 中華電信MOD http://mod.cht.com.tw/