在推薦系統(recommender system)相關的研究領域中，目前大多以針對個人喜好進行推薦為主。主要作法為記錄個人在系統中的行為模式，待下一次使用者(user)使用系統時以使用者的歷史喜好或興趣進行推薦。然而日常生活中許多消費行為或休閒活動皆非一人單獨進行，大多會與親朋好友成群結伴，以群體(group)的形式進行活動，例如看電影、旅遊或用餐等群體活動，個人化群體推薦系統因此無法滿足諸如此類的應用情境。過去在群體推薦系統中慣用的方法是將群體中成員對物件的喜好進行合併，成為群體對物件的評比，這樣的作法忽略了群體中成員的人格特質與成員間的互動模式，因此產生的評比結果將無法反映群體對物件的實際喜好。本文提出的類神經網路為訓練基礎的群體推薦系統，是以群體中個別成員對物件的評比以及群體對物件的評比，進行神經網路中權重的訓練，來模擬群體成員間的相互影響現象，若缺少個人評比的情況之下則使用傳統的協合過濾式演算法對個人評比做預測，藉以彌補個人評比不足的問題。實驗評估本系統可以準確地預測群體對物件的評比，且在訓練過程中，選擇適當的學習速率將有利於訓練權重值的精確度。群體推薦系統與個人化推薦系統不同的地方在於可以較人性化的滿足每位使用者從事活動時的需求，考量每位使用者的感受，這是一般個人化推薦系統較無法達成的功能。

In the research field of Recommender System, the personalized recommender system has always been regarded as the main trend. The main operation is to record the pattern of personal behavior in the system and then the system will recommend users which program to use according to users’ preferences. However, consumer behaviors and recreational activities are not both formed by one single individual, many of which will be made by groups. For example, when relatives and friends get together to go to see movies, go travelling or having meals, the single user recommender system can’t achieve the application targets for above situations. In the past, the group recommender system intended to combine users’ preference on the same aspect to achieve different variety of measurement. However, this approach ignores individual member’s characteristics and the pattern of how each member interacts with others; such that this sort of measurement can’t truly reflect real interest on the same issue. The main target of our research is to develop a group recommender system based on neural network training algorithms. We proposed to train and get weights in the neural network and to simulate phenomena made by the interaction among groups by measuring the same issue made by each individual or the whole group. Finally, we evaluate our approach experimentally and compare it in different parameter of network. The experimental result shows that we can achieve the function of being user-friendly by algorithm in the group recommender system that can’t be achieve by algorithm in the personalized recommender system.

[1] 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.
[2] M. J. Pazzani and D. Billsus, “Content-based recommendation systems,” Lecture Notes in Computer and Information Science, pp.325-341, 2007.
[3] F. Ricci, L. Rokach, B. Shapira, and P.B. Kantor, “Recommender system handbook,” Publisher: Springer; 1st Ed., Oct. 2010.
[4] T. Hofmann, “Collaborative filtering via Gaussian probabilistic latent semantic analysis,” Int. ACM SIGIR conf. Research and Development in Information Retrieval, pp.259-266, 2003.
[5] 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.
[6] 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.
[7] A. Paterek, “Improving regularized singular value decomposition for collaborative filtering,” In Proc. of the KDD Cup and Workshop, 2007.
[8] 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.
[9] 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.
[10] 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.
[11] 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.
[12] 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.
[13] R. Burke, “Hybrid recommender systems: Survey and experiments,” User Modeling and User-Adapted Interaction, vol.12, pp.331-370, Nov. 2002.
[14] 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.
[15] 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.
[16] G. C. Homans, “The human group,” Transaction Publishers, New York: Harcourt, Brace, & World, Jan. 1991.
[17] A. P. Hare, “Handbook of small group research,” Free Pr; 2nd ed., Nov. 1976.
[18] H. Bonner, “Group dynamics: principles and applications,” New York: Ronald Press Company, 1959.
[19] D. Cartwright and A.Zander, “Group dynamics: research and theory,” New York: Harper & Row, 3rd Ed., 1968.
[20] E. P. Hollander, “Principles and methods of social psychology,” New York: Oxford University Press, 1971.
[21] 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.
[22] G.A. Carpenter, S. Grossberg, and J.H. Reynolds, “ARTMAP: Supervised real-time learning and classification of non-stationary data by a self-organizing neural network,” In Proc. IEEE conf. on Neural Networks for Ocean Engineering, vol.4, pp.565-588, 1991.
[23] 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.
[24] 莊清男(民94)。協同過濾式群體推薦，國立中央大學資訊管理研究所碩士論文。
[25] 李威廷(民97)。以詩詞本體論與類神經網路為基礎之唐詩推薦系統，國立中央大學資訊工程研究所碩士論文。
[26] 陳贊仁(民98)。以倒傳遞網路設計籃球運動彩券推薦模式，大同大學資訊工程研究所碩士論文。
[27] T.H. Chang, “Using back-propagation network to predict proper cyclosporine dosage in patients after kidney transplantation,” Thesis for Master of Science, Department of Computer Science and Engineering, Tatung University, July 2008.
[28] W.C. Cheng, “The study of using artificial neural network to inspect the insurance of insured unit,” Thesis for Master of Science, Department of Computer Science and Engineering, Tatung University, Jan. 2009.
[29] J. Feng, “Personalized context-aware rating prediction model and recommendation approach based on neural network,” IEEE International conf. on Internet Technology and Applications, 2010.
[30] 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.