現今有許多數位遊戲發行平台誕生，而其中使用人數最多的便是由Valve公司所推出的Steam平台。它不但提供遊戲販售的功能，還提供了數位版權管理功能，讓使用者可以使用Steam來啟動遊戲並遊玩，也因此使用者的遊玩行為能夠被觀測到。同時，Steam也提供了社群功能，讓使用者可以在平台上建立社群及互動。因此Steam不但是一個遊戲販售平台，也是一個遊戲管理平台，同時還是一個社交平台。於是我們嘗試在這樣的平台上，利用其多功能性的特色，去幫使用者解決尋找遊戲夥伴的問題。我們利用平台上的公開資料，也就是使用者的遊戲清單、遊戲時數、即時動態、好友列表去計算出使用者間是否適合一起玩遊戲，並為其尋找出適合的遊戲夥伴，組成遊戲團體。

There are many digital game distribution platforms today, and Steam, which developed by Valve Corporation, has the most users. Steam not only provides game selling features, but also provides digital rights management features, allowing users to launch games and play it on Steam. That makes the user's playing behavior can be observed. At the same time, Steam also provides community features that enable users to build social communities and interacting with each other on the platform. Therefore, Steam is not only a game selling platform, but also a game management platform and a social platform. Due to the versatility of Steam, we try to solve the problem of finding game partners. We use the public information on Steam, that is, the user's game list, play time, current activity status, and friend list to calculate whether the user is suitable for playing games together by similarity. And then find suitable game partners for them to form a gaming group.

第一章、緒論 1
1.1 研究背景 1
1.2 研究動機與目的 1
第二章、文獻探討 3
第三章、問題描述 9
第四章、資料集 10
4.1 資料集分析 10
第五章、方法 12
5.1 遊戲相似度 12
5.2 時段相似度 13
5.3 社交距離 15
5.4 適合度 15
5.5 演算法 15
第六章、實驗 17
6.1 實驗內容 17
6.2 計算 19
6.3 結果比較與分析 20
第七章、結論與未來展望 22
7.1 研究限制 22
7.2 未來展望 22
參考資料 23

[1] A. Pathak, K. Gupta, and J. McAuley, “Generating and Personalizing Bundle Recommendations on Steam,” Proc. 40th Int. ACM SIGIR Conf. Res. Dev. Inf. Retr. - SIGIR ’17, pp. 1073–1076, 2017.
[2] R. Sifa, S. Augustin, A. Drachen, and C. Bauckhage, “Large-Scale Cross-Game Player Behavior Analysis on Steam,” Elev. AAAI Conf. Artif. Intell. Interact. Digit. Entertain., pp. 198–204, 2015.
[3] L. Backstrom, D. Huttenlocher, J. Kleinberg, and X. Lan, “Group formation in large social networks,” Proc. 12th ACM SIGKDD Int. Conf. Knowl. Discov. data Min. - KDD ’06, p. 44, 2006.
[4] S. B. Roy, L. V. S. Lakshmanan, and R. Liu, “From Group Recommendations to Group Formation,” SIGMOD 2015 Proc. 2015 ACM SIGMOD Int. Conf. Manag. Data, pp. 1603–1616, 2015.
[5] M. Wessner and H. -R. Pfister, “Group formation in computer-supported collaborative learning,” Proc. 2001 Int. ACM Siggr. Conf. Support. Gr. Work - Gr. ’01, p. 24, 2001.
[6] E. Martin and P. Paredes, “Using learning styles for dynamic group formation in adaptive collaborative hypermedia systems,” Proc. 1st Int. Work. Adapt. Hypermedia Collab. Web-based Syst., pp. 188–198, 2004.
[7] A. Ounnas, H. C. Davis, and D. E. Millard, “A framework for semantic group formation in education,” Educ. Technol. Soc., vol. 12, no. 4, pp. 43–55, 2009.
[8] J. Moreno, D. A. Ovalle, and R. M. Vicari, “A genetic algorithm approach for group formation in collaborative learning considering multiple student characteristics,” Comput. Educ., vol. 58, no. 1, pp. 560–569, 2012.
[9] Y. A. Pollalis and G. Mavrommatis, “Using similarity measures for collaborating groups formation: A model for distance learning environments,” Eur. J. Oper. Res., vol. 193, no. 2, pp. 626–636, 2009.
[10] I. Srba and M. Bielikova, “Dynamic Group Formation as an Approach to Collaborative Learning Support,” IEEE Trans. Learn. Technol., vol. PP, no. 99, pp. 173–186, 2014.
[11] M. Gaston and J. Simmons, “Adapting network structure for efficient team formation,” Proc. AAAI 2004 Fall, 2004.
[12] T. Lappas, K. Liu, and E. Terzi, “Finding a team of experts in social networks,” Proc. 15th ACM SIGKDD Int. Conf. Knowl. Discov. data Min. - KDD ’09, p. 467, 2009.
[13] M. Kargar and A. An, “Discovering top-k teams of experts with/without a leader in social networks,” Proc. 20th ACM Int. Conf. Inf. Knowl. Manag. - CIKM ’11, p. 985, 2011.
[14] C. Castillo, A. Anagnostopoulos, L. Becchetti, A. Gionis, and S. Leonardi, “Power in Unity : Forming Teams in Large-Scale Community Systems,” 19th ACM Conf. Conf. Inf. Knowl. Manag. CIKM ’10, pp. 599–608, 2010.
[15] A. Anagnostopoulos, L. Becchetti, C. Castillo, A. Gionis, and S. Leonardi, “Online team formation in social networks,” Proc. 21st Int. Conf. World Wide Web, no. APRIL, pp. 839–848, 2012.
[16] A. Majumder, S. Datta, and K. V. M. Naidu, “Capacitated team formation problem on social networks,” Proc. 18th ACM SIGKDD Int. Conf. Knowl. Discov. data Min. - KDD ’12, p. 1005, 2012.
[17] M. Kargar, M. Zihayat, and A. An, “Finding Affordable and Collaborative Teams from a Network of Experts,” in Proceedings of the 2013 SIAM International Conference on Data Mining, Philadelphia, PA: Society for Industrial and Applied Mathematics, pp. 587–595 , 2013.
[18] A. Gajewar and A. D. Sarma, “Multi-skill collaborative teams based on densest subgraphs,” Proc. 12th SIAM Int. Conf. Data Mining, SDM 2012, pp. 165–176, 2012.
[19] S. Rangapuram, T. Bühler, and M. Hein, “Towards realistic team formation in social networks based on densest subgraphs,” in Proceedings of the 22nd international conference on World Wide Web - WWW ’13, pp. 1077–1088, 2013.
[20] M. Wright and Y. Vorobeychik, “Mechanism Design for Team Formation,” Proc. 29th AAAI Conf. Artif. Intell., pp. 1050–1056, 2015.
[21] K. Li, W. Lu, S. Bhagat, L. V. S. Lakshmanan, and C. Yu, “On social event organization,” Proc. 20th ACM SIGKDD Int. Conf. Knowl. Discov. data Min. - KDD ’14, pp. 1206–1215, 2014.
[22] J. She, Y. Tong, and L. Chen, “Utility-Aware Social Event-Participant Planning,” in Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data - SIGMOD ’15, pp. 1629–1643, 2015.
[23] J. Yang and J. Leskovec, “Overlapping community detection at scale,” in Proceedings of the sixth ACM international conference on Web search and data mining - WSDM ’13, p. 587, 2013.
[24] R. Balasubramanyan and W. W. Cohen, “Block-LDA: Jointly modeling entity-annotated text and entity-entity links,” Proc. 2011 SIAM Int. Conf. Data Min., pp. 450–461, 2011.
[25] Z. Xu, Y. Ke, Y. Wang, H. Cheng, and J. Cheng, “A model-based approach to attributed graph clustering,” Proc. 2012 Int. Conf. Manag. Data - SIGMOD ’12, p. 505, 2012.
[26] Y. Sun, C. C. Aggarwal, and J. Han, “Relation strength-aware clustering of heterogeneous information networks with incomplete attributes,” Proc. VLDB Endow., vol. 5, no. 5, pp. 394–405, Jan.2012.
[27] J. Yang, J. McAuley, and J. Leskovec, “Community detection in networks with node attributes (extended),” Proc. - IEEE Int. Conf. Data Mining, ICDM, pp. 1151–1156, 2013.
[28] M. Sozio and A. Gionis, “The community-search problem and how to plan a successful cocktail party,” Proc. 16th ACM SIGKDD Int. Conf. Knowl. Discov. data Min. - KDD ’10, p. 939, 2010.
[29] E. Galbrun, B. Golshan, A. Gionis, and E. Terzi, “Finding low-tension communities,” in Proceedings of the 2017 SIAM International Conference on Data Mining, Philadelphia, PA: Society for Industrial and Applied Mathematics pp. 336–344, 2017,.