傳統網路社群的信任與名聲管理機制相當簡單，通常是由使用者或管理者給予服務提供者評分，會員的可信度與其所得之分數呈正相關。這種簡單機制對於惡意(malicious)、不誠實(dishonest)或挑釁(troll)的會員，並無法提供有效的管理功能，更可能受到惡意成員的扭曲或利用，影響網路社群的正常發展。為解決上述問題，本研究綜合節點分支度、中心性等多種社群網路分析指標，運用線性迴歸與類神經網路，分別以線性與非線性方式加以組合，期能提供正確的社群網路成員影響力與信任度。其次，我們亦考量影響力之極性(polarity)，期能進一步標示出社群中之好群體與壞群體。此外，面對大型社群網路，各種指標的計算往往曠日廢時，本研究亦探討利用不同的中心性指標，預測運算成本較高之指標的可能性。本研究由PTT討論區下載發文資料進行實驗，結果顯示本研究提出之影響力預測方法與實際值具有高度相聯。其次，約有超過70%的成員在社群中的影響力排名預測，誤差不超過25%，上述結果顯示本研究提出方法之有效性。我們也利用四種不同中心性指標來預測中介中心性，結果呈高度相關。此結果對於社群網路分析之成本縮減，提供另一種可行之道。

Trust and reputation management mechanism is quite simple in the traditional Internet community. The feedback score of a member is usually given by other users or site managers. And, the amount of score is positively correlated with the credibility of the members. Such a simple mechanism is unable to provide effective management for malicious, dishonest or troll members but more likely to be distorted or exploited by those abnormal members, which then affecting the normal development of the Internet community. To solve these problems, this research integrates a variety of social network analysis index of degree, centrality, etc. Using linear regression and Artificial Neural Network to combine these indices by linear and nonlinear manner separately. And, use the result to provide correct influence and trust of social networks members. Secondly, we also consider the influence of the polarity, marked a further stage in the community of good groups and bad groups. In addition, the face of large-scale social network, to calculate various index often waste time and drawn out. This research also explores examine the possibility of using different centrality indices to substitute that of high computation cost. Data download from PTT forum are used for experiment, and the results show the effectiveness of the proposed prediction methods. Secondly, the results also show that the prediction error of influence ranking is less than 25% for more than 70% community members. It demonstrate the effectiveness of the proposed method. We also use four different centrality index to predict the betweenness centrality, and the results were highly correlated, which provides another viable way for reducing the cost of social network analysis.

第一章緒論 1
1.1研究背景 1
1.2研究動機 2
1.3研究目的 4
1.4章節架構 5
第二章文獻探討 6
2.1社群網路(Social Network) 6
2.2社群網路分析(Social network analysis, SNA) 7
2.3最短路徑演算法(Shortest path algorithm) 10
2.4類神經網路(Artificial Neural Network, ANN) 11
第三章社群網路成員影響力與信任度計算	 14
3.1社群網路影響力指標 14
3.2影響力指標分析 18
3.3綜合影響力計算 21
第四章系統實作 25
4.1實驗設定 25
4.2社群使用者影響力預測 27
4.2.1計算使用者之各項指標 27
4.2.2使用線性組合方式預測影響力 28
4.2.3使用非線性組合方式預測影響力 33
4.3使用其他中心性指標預測Betweenness Centrality 34
第五章結論 36
參考文獻 38
附錄A 各資料蒐集月份10次實驗結果統計 41

表目錄
表3-1：PTT討論區(黑特版)各種社群中心性指標前20名會員名單 20
表4-1：每月樣本數 29
表4-2：線性迴歸預測之影響力結果與實際值之平均相關度(correlation) 29
表4-3：線性迴歸預測之影響力排名平均誤差 30
表4-4：以排名間距呈現各月份之影響力預測誤差累計比率 32
表4-5：非線性排名誤差平均值 34
表4-6：運用Degree、CC、AU、Hub等指標計算BC值 35

圖目錄
圖2-1：社交網路圖 7
圖2-2：Floyd-Warshall演算法 11
圖2-3：單一隱藏層之神經網路架構圖 13
圖3-1：分支度中心性社群網路圖範例 15
圖3-2：中介中心性社交網路圖範例 16
圖3-3：Authority & Hub 演算法 (Kleinberg, 1999) 18
圖3-4：使用類神經網路組合指標值，計算成員之影響力 22
圖4-1：影響力排名平均差距累計百分比 33

1.Boyd, Danah, and Nicole Ellison. "Social network sites: definition, history, and scholarship." IEEE Engineering Management Review 3.38 (2010): 16-31.
2.Chen, Jia, et al. "A trust and reputation model considering overall peer consulting distribution." Systems, Man and Cybernetics, Part A: Systems and Humans, IEEE Transactions on 42.1 (2012): 164-177.
3.Cohen, J. (1977). Statistical power analysis for the behavioral science. Routledge.
4.De Veaux, Richard D., and Lyle H. Ungar. A brief introduction to neural networks. Technical Report, Williams College, Williamstown, MA, 1997.
5.Domingos, Pedro, and Matt Richardson. "Mining the network value of customers." Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, 2001.
6.Franks, Henry, Nathan Griffiths, and Sarabjot Singh Anand. "Learning influence in complex social networks." Proceedings of the 2013 international conference on Autonomous agents and multi-agent systems. International Foundation for Autonomous Agents and Multiagent Systems, 2013.
7.Hanneman, Robert A., and Mark Riddle. "Introduction to social network methods." (2005).
8.Hoppe, Bruce, and Claire Reinelt. "Social network analysis and the evaluation of leadership networks." The Leadership Quarterly 21.4 (2010): 600-619.
9.Kleinberg, Jon M. "Authoritative sources in a hyperlinked environment." Journal of the ACM (JACM) 46.5 (1999): 604-632.
10.Kaszuba, Tomasz, Albert Hupa, and Adam Wierzbicki. "Advanced feedback management for internet auction reputation systems." Internet Computing, IEEE 14.5 (2010): 31-37.
11.Kempe, David, Jon Kleinberg, and Éva Tardos. "Maximizing the spread of influence through a social network." Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, 2003.
12.Madduri, Kamesh, et al. "An experimental study of a parallel shortest path algorithm for solving large-scale graph instances." Proceedings of the Meeting on Algorithm Engineering & Expermiments. Society for Industrial and Applied Mathematics, 2007.
13.Ma, Jian, Ke-Ping Li, and Li-yan Zhang. "A parallel floyd-warshall algorithm based on tbb." Information Management and Engineering (ICIME), 2010 The 2nd IEEE International Conference on. IEEE, 2010.
14.Ortega, F. Javier, et al. "Propagation of trust and distrust for the detection of trolls in a social network." Computer Networks 56.12 (2012): 2884-2895.
15.Saha, A., Pal, M. , Pal, K. T., "An optimal parallel algorithm for solving all-pairs shortest paths problem on circular-arc graphs," Journal of Applied Mathematics and Computing, March 2005, Volume 17, Issue 1, pp 1-23. 
16.Tavakolifard, Mozhgan, and Kevin C. Almeroth. "Social computing: an intersection of recommender systems, trust/reputation systems, and social networks." Network, IEEE 26.4 (2012): 53-58.
17.Watts, Duncan J. "A simple model of global cascades on random networks."Proceedings of the National Academy of Sciences 99.9 (2002): 5766-5771.
18.尹相志.(2009). SQL Server 2008 Data Mining資料採礦.
19.李政道. 在Twitter上使用文字探勘技術尋找具有影響力的使用者. 國立成功大學醫學研究所碩士論文, 2013.
20.李春雄.(2009). 資料結構使用Java.
21.巫鎧戎. 虛擬社群網路口碑影響政治參與行為之研究-以PTT平台為例. 國立雲林科技大學資訊管理系碩士論文, 2013.
22.批踢踢實業坊. 批踢踢實業坊首頁. 擷取自 批踢踢實業坊網頁版首頁：https://www.ptt.cc/index.html
23.翁豪箴. 考量服務品質之多屬性線上拍賣名聲系統. 淡江大學資訊管理學系碩士論文, 2009.
24.陳明謙. 社群影響力分析於社群網路中. 國立中央大學資訊工程學系碩士論文, 2013.
25.張淳矞. 以動態網絡分析探討網路社群口碑與購買態度之關係. 國立交通大學傳播研究所碩士論文, 2009.
26.劉嵋璊. 社會網絡平台資訊擴散之研究-以PTT與Facebook為例. 國立高雄大學亞太工商管理學系碩士論文, 2012.
27.蘇昭安. 應用倒傳遞類神經網路在颱風波浪預報之研究. 國立台灣大學工程科學與海洋工程學系碩士論文, 2003.