在社群網路中，訊息傳遞的非常快速。使用者接收訊息與否取決於使用者之間的關係緊密程度，透過分析社群網路中的使用者關係緊密程度可以應用於多個領域，像是廣告行銷或是網路市場行銷。在近幾年，類神經網絡受到大眾廣大的研究，此篇研究中，我們透過類神經網絡學習使用者之間的關係緊密程度，透過原始的類神經網絡我們可以很好的學習使用者間的關係緊密程度，除此之外我們更近一步使用社區的資訊作為學習此問題的特徵，我們透過卷積類神經網絡提取社區的資訊。我們在合成的資料和現實社會的資料上試驗我們的方法，實驗結果顯示我們在精準度表現比其他的方法更為優異，相較於其他方法我們的方法也有著較低的平均絕對誤差

In social networks, information spread quickly through users. Whether an user will adopt theinformation depends on social influence between users. Learning social influence between userson social networks, such as Twitter and Facebook, have been extensively studied in a decadewhich plays an important role in viral marketing and online advertising. In this work, we studythe social influence by artificial neural network since it has attracted massive attention in years.We first address our problem on deep neural network by directly utilizing the diffusion traces fortraining the deep neural network. Furthermore, we use community information as additionalinformation for training convolution neural network. This framework has been evaluated on both synthetic and real world data sets. Experimental results confirms better accuracy andlower mean absolute error of our model over all compared methods.

[1] R. Agrawal, J. Gehrke, D. Gunopulos, and P. Raghavan.Automatic subspace clustering ofhigh dimensional data for data mining applications, volume 27. ACM, 1998.
[2] A. Anagnostopoulos, L. Becchetti, C. Castillo, A. Gionis, and S. Leonardi. Online teamformation in social networks. InProceedings of the 21st international conference on WorldWide Web, pages 839–848. ACM, 2012.
[3] S. Ara ́ujo, J. Wetterlind, J. Dematt^e, and B. Stenberg. Improving the prediction perfor-mance of a large tropical vis-nir spectroscopic soil library from brazil by clustering intosmaller subsets or use of data mining calibration techniques.European Journal of SoilScience, 65(5):718–729, 2014.
[4] E. Bakshy, D. Eckles, R. Yan, and I. Rosenn. Social influence in social advertising: evi-dence from field experiments. InProceedings of the 13th ACM Conference on ElectronicCommerce, pages 146–161. ACM, 2012.
[5] M. E. Celebi, H. A. Kingravi, and P. A. Vela. A comparative study of efficient initial-ization methods for the k-means clustering algorithm.Expert Systems with Applications,40(1):200–210, 2013.
[6] Y.-C. Chen, H.-S. Ma, and J.-W. Huang. Multi-state open opinion model based on posi-tive and negative social influences. InAdvances in Social Networks Analysis and Mining(ASONAM), 2015 IEEE/ACM International Conference on, pages 170–177. IEEE, 2015.
[7] C.-K. Chou and M.-S. Chen. Multiple factors-aware diffusion in social networks. InPacific-Asia Conference on Knowledge Discovery and Data Mining, pages 70–81. Springer, 2015.
[8] P. Domingos and M. Richardson. Mining the network value of customers. InProceedingsof the seventh ACM SIGKDD international conference on Knowledge discovery and datamining, pages 57–66. ACM, 2001.
[9] N. Du, B. Wu, X. Pei, B. Wang, and L. Xu. Community detection in large-scale socialnetworks. InProceedings of the 9th WebKDD and 1st SNA-KDD 2007 workshop on Webmining and social network analysis, pages 16–25. ACM, 2007.
[10] F. J. Elgar, T.-K. Pf ̈ortner, I. Moor, B. De Clercq, G. W. Stevens, and C. Currie. So-cioeconomic inequalities in adolescent health 2002–2010: a time-series analysis of 34 coun-tries participating in the health behaviour in school-aged children study.The Lancet,385(9982):2088–2095, 2015.
[11] P. Fournier-Viger, A. Gomariz, T. Gueniche, A. Soltani, C.-W. Wu, V. S. Tseng, et al.Spmf: a java open-source pattern mining library.Journal of Machine Learning Research,15(1):3389–3393, 2014.
[12] J. Goldenberg, B. Libai, and E. Muller. Using complex systems analysis to advance mar-keting theory development: Modeling heterogeneity effects on new product growth throughstochastic cellular automata.Academy of Marketing Science Review, 2001:1, 2001.
[13] M. Granovetter. Threshold models of collective behavior.American journal of sociology,83(6):1420–1443, 1978.
[14] S. Haykin and N. Network. A comprehensive foundation.Neural Networks, 2(2004):41,2004.
[15] D. Kempe, J. Kleinberg, and ́E. Tardos. Maximizing the spread of influence through asocial network. InProceedings of the ninth ACM SIGKDD international conference onKnowledge discovery and data mining, pages 137–146. ACM, 2003.
[16] M. Kimura, K. Saito, and H. Motoda. Blocking links to minimize contamination spread ina social network.ACM Transactions on Knowledge Discovery from Data (TKDD), 3(2):9,2009.
[17] D. Kingma and J. Ba. Adam: A method for stochastic optimization.arXiv preprintarXiv:1412.6980, 2014.
[18] J. Leskovec, K. J. Lang, and M. Mahoney. Empirical comparison of algorithms for networkcommunity detection. InProceedings of the 19th international conference on World wideweb, pages 631–640. ACM, 2010.
[19] C.-T. Li and M.-K. Shan. Team formation for generalized tasks in expertise social networks.InSocial Computing (SocialCom), 2010 IEEE Second International Conference on, pages9–16. IEEE, 2010.
[20] R.-H. Li and J. X. Yu. Scalable diversified ranking on large graphs.IEEE Transactionson Knowledge and Data Engineering, 25(9):2133–2146, 2013.
[21] M. Liu and J. Qu. Mining high utility itemsets without candidate generation. InProceed-ings of the 21st ACM international conference on Information and knowledge management,pages 55–64. ACM, 2012.
[22] A. Majumder, S. Datta, and K. Naidu. Capacitated team formation problem on socialnetworks. InProceedings of the 18th ACM SIGKDD international conference on Knowledgediscovery and data mining, pages 1005–1013. ACM, 2012.
[23] W. S. McCulloch and W. Pitts. A logical calculus of the ideas immanent in nervousactivity.The bulletin of mathematical biophysics, 5(4):115–133, 1943.
[24] R. Mishra and A. Choubey. Discovery of frequent patterns from web log data by usingfp-growth algorithm for web usage mining.International Journal of Advanced Research inComputer Science and Software Engineering, 2(9), 2012.
[25] T. Murata and S. Moriyasu. Link prediction of social networks based on weighted prox-imity measures. InProceedings of the IEEE/WIC/ACM International Conference on WebIntelligence, WI ’07, pages 85–88, Washington, DC, USA, 2007. IEEE Computer Society.
[26] M. E. Newman. The structure and function of complex networks.SIAM review, 45(2):167–256, 2003.
[27] M. E. Newman and M. Girvan. Finding and evaluating community structure in networks.Physical review E, 69(2):026113, 2004.
[28] L. T. Nguyen, B. Vo, T.-P. Hong, and H. C. Thanh. Classification based on associationrules: A lattice-based approach.Expert Systems with Applications, 39(13):11357–11366,2012.
[29] M. A. Porter, J.-P. Onnela, and P. J. Mucha. Communities in networks.Notices of theAMS, 56(9):1082–1097, 2009.
[30] U. N. Raghavan, R. Albert, and S. Kumara. Near linear time algorithm to detect commu-nity structures in large-scale networks.Physical review E, 76(3):036106, 2007.
[31] T. Rakthanmanon, B. Campana, A. Mueen, G. Batista, B. Westover, Q. Zhu, J. Zakaria,and E. Keogh. Addressing big data time series: Mining trillions of time series subsequencesunder dynamic time warping.ACM Transactions on Knowledge Discovery from Data(TKDD), 7(3):10, 2013.
[32] F. Rosenblatt. The perceptron: A probabilistic model for information storage and organi-zation in the brain.Psychological review, 65(6):386, 1958.
[33] S. Scellato, A. Noulas, and C. Mascolo. Exploiting place features in link prediction onlocation-based social networks. InProceedings of the 17th ACM SIGKDD internationalconference on Knowledge discovery and data mining, pages 1046–1054. ACM, 2011.
[34] C. Tsourakakis, F. Bonchi, A. Gionis, F. Gullo, and M. Tsiarli. Denser than the densestsubgraph: extracting optimal quasi-cliques with quality guarantees. InProceedings of the19th ACM SIGKDD international conference on Knowledge discovery and data mining,pages 104–112. ACM, 2013.
[35] D. Wang, D. Pedreschi, C. Song, F. Giannotti, and A.-L. Barabasi. Human mobility,social ties, and link prediction. InProceedings of the 17th ACM SIGKDD internationalconference on Knowledge discovery and data mining, pages 1100–1108. ACM, 2011.
[36] D. J. Watts. A simple model of global cascades on random networks.Proceedings of theNational Academy of Sciences, 99(9):5766–5771, 2002.
[37] J. Xie and B. K. Szymanski. Towards linear time overlapping community detection insocial networks. InPacific-Asia Conference on Knowledge Discovery and Data Mining,pages 25–36. Springer, 2012.
[38] H. Yu, J. Yang, and J. Han. Classifying large data sets using svms with hierarchicalclusters. InProceedings of the ninth ACM SIGKDD international conference on Knowledgediscovery and data mining, pages 306–315. ACM, 2003.
[39] D. Zhang, J. He, and R. Lawrence. Mi2ls: multi-instance learning from multiple infor-mationsources. InProceedings of the 19th ACM SIGKDD international conference onKnowledge discovery and data mining, pages 149–157. ACM, 2013.
[40] B. Zheng, K. Thompson, S. S. Lam, S. W. Yoon, and N. Gnanasambandam. Customers’behavior prediction using artificial neural network. InIIE Annual Conference. Proceedings,page 700. Institute of Industrial and Systems Engineers (IISE), 2013.