推薦專家系統近年來有諸多研究與應用，其目的是希望能藉由分析專家與提問者間之關聯，來獲取最適合回答該問題之專家。然而此研究領域存在冷啟動問題，使得新進入者，缺乏可分析之數據，以致無法準確推送目標給用戶。為解決此問題，本篇論文將研究專注在CQA問答系統之推薦專家上，透過結合Quora與Facebook社群媒體資料，將社群問答網站加入使用者臉書資訊之外部特徵，降低新使用者與新問題之冷啟動問題。本論文實驗了在傳統Aspect Model與SVD++模型上，結合不同社群資料的方法，最終結果為單一使用Aspect Model 模型，有較高的準確率。

There are many studies and applications concerning the expert recommendation systems in recent years, which aim to select experts eligible to answer questions by analyzing associations between experts and questioners. However, a cold start issue exists. A newcomer cannot be analyzed because of a lack of information. To address this issue, we proposed combining user information derived from CQA sites, e.g., Quora, and social media sites, e.g., Facebook to recommend experts. We used aspect model and SVD++ to select experts. The experiment results showed that the aspect model alone had better performance.

第一章 緒論 1
1.1 研究背景 1
1.2 研究動機 2
1.3 研究目的與問題 2
1.4 文獻探討 3
1.4.1 推薦系統研究現況 3
1.4.2 社群問答網站中尋找專家的相關研究 6
第二章 研究方法 11
2.1 前言 11
2.2 尋找專家 11
2.2.1 Aspect model 13
2.2.2 SVD++ 17
2.3 實驗設計 20
第三章 實驗結果 23
3.1 只考慮Quora社群問答網站資訊 23
3.2 整合Quora社群問答網站資訊與FaceBook社群媒體資訊 26
3.3 結論 28
第四章 未來展望 29
參考文獻 31

[1] Yahoo! Answers, https://answers.yahoo.com/
[2] Quantcast profile for Yahoo! Answers, Quantcast.com, Retrieved April 20, 2012.
[3] Quora, https://www.quora.com/
[4] Stack Overflow, http://stackoverflow.com/
[5] Baidu Knows, http://zhidao.baidu.com/
[6] Answers, http://www.answers.com/
[7] T.C. Zhou, M.R. Lyu, and I. King, "A Classification-based approach to question routing in community question answering," in Proceedings of the 21st International Conference on World Wide Web, 2012, pp. 783-790.
[8] D. Geiger and M. Schader, "Personalized task recommendation in crowdsourcing information systems - Current state of the art," Decision Support Systems, vol. 65, pp. 3-16, 2014.
[9] G. Salton, "The transformation, analysis, and retrieval of information by computer," in Automatic text processing, MA, United States, 1989.
[10] R. Baeza-Yates and B. Ribeiro-Neto, "Alternative Alegebraic Model," in Modern Information Retrieval, U.S., Harlow, 1999, ch. 2, pp.19-69.
[11] J. Han, M. Kamber, and J. Pei, "Data Mining," in Data mining: Concepts and techniques, 3ed. Waltham, USA, 2011, ch. 3, pp.95-117.
[12] K. Lang, "Newsweeder: learning to filter netnews," in Proceedings of the 12st International Conference on Machine Learning, 1995, pp. 331-339.
[13] R.J. Mooney and L. Roy, "Content-based book recommending using learning for text categorization," in Proceedings of the fifth ACM Conference on Digital Libraries, 1999, pp. 195-204.
[14] C.D. Manning, P. Raghavan and H. Schütze, "Introduction to information retrieval," Cambridge University Press. 2008.
[15] M. Pazzani and D. Billsus, "Learning and revising user profiles: The identification of interesting web sites," Machine Learning, vol. 27, pp. 313-331, 1997.
[16] M. Pazzani, "A framework for collaborative, content-based, and demographic filtering," Artificial Intelligence Rev., pp. 393-408, 1999.
[17] N. Littlestone, "Learning quickly when irrelevant attributes abound: A new linear-threshold algorithm," Machine Learning, vol. 2, pp. 285–318, 1988.
[18] J.S. Breese, D. Heckerman, and C. Kadie, "Empirical analysis of predictive algorithms for collaborative filtering," in Proceedings of 14th Conference on Uncertainty in Artificial Intelligence, 1998, pp. 43-52.
[19] D. Chickering, D. Heckerman, and C. Meek, "A Bayesian approach to learning Bayesian networks with local structure," in Proceedings of 13th Conference on Uncertainty in Artificial Intelligence, 1997, pp. 80-89.
[20] K. Goldberg, T. Roeder, D. Gupta, and C. Perkins, "Eigentaste: A constant time collaborative filtering algorithm," Information Retrieval, vol. 4, no. 2, pp. 133-151, July 2001.
[21] T. Hofmann, "Collaborative filtering via Gaussian probabilistic latent semantic analysis," in Proceedings of 26th International ACM SIGIR Conference, 2003, pp. 259-266.
[22] T. Hofmann, "Learning what people (don't) want," in Proceedings of the European Conference on Machine Learning, 2001, pp. 214-225.
[23] D. Blei, A. Ng, and M. Jordan, "Latent dirichlet allocation," Journal of Machine Learning Research, vol.3, pp. 993-1022, 2003.
[24] M. Claypool, A. Gokhale, T. Miranda, P. Murnikov, D. Netes, and M. Sartin, "Combining content-based and collaborative filters in an online newspaper," in Proceedings of ACM SIGIR ’99 Workshop Recommender Systems: Algorithms and Evaluation, 1999.
[25] D. Billsus and M. Pazzani, "User modeling for adaptive news access," User Modeling and User-Adapted Interaction, vol.10, pp. 147-180, 2000.
[26] T. Tran and R. Cohen, "Hybrid recommender systems for electronic commerce," Proceedings of Knowledge-Based Electronic Markets, Papers from the AAAI Workshop, Technical Report WS-00-04, AAAI Press, 2000.
[27] N. Good, J.B. Schafer, J.A. Konstan, A. Borchers, B. Sarwar, J.L. Herlocker, and J. Riedl, "Combining collaborative filtering with personal agents for better recommendations," in Proceedings of Conference American Association for Artificial Intelligence (AAAI-99), 1999, pp. 439-446.
[28] P. Melville, R.J. Mooney, and R. Nagarajan, "Content-boosted collaborative filtering for improved recommendations," in Proceedings of 18th National Conference on Artificial Intelligence, 2002, pp. 187-192.
[29] I. Soboroff and C. Nicholas, "Combining content and collaboration in text filtering, " in Proceedings of International Joint Conference Artificial Intelligence Workshop: Machine Learning for Information Filtering, 1999, pp. 86-91.
[30] A. Popescul, L.H. Ungar, D.M. Pennock, and S. Lawrence, "Probabilistic models for unified collaborative and content-based recommendation in sparse-data environments," in Proceedings of 17th Conference on Uncertainty in Artificial Intelligence, 2001, pp. 437-444.
[31] A.I. Schein, A. Popescul, L.H. Ungar, and D.M. Pennock, "Methods and metrics for cold-start recommendations," in Proceedings of 25th annual international ACM SIGIR conference on Research and development in information retrieval, 2002, pp. 253-260.
[32] J.S. Pedro and A. Karatzoglou, "Question recommendation for collaborative question answering systems with RankSLDA," in Proceedings of the 8th ACM Conference on Recommender systems, 2014, pp. 193-200.
[33] D.M. Blei and J.D. McAulie, "Supervised topic models," in Proceedings of Neural Information Processing Systems Conference, 2007.
[34] D. Hu, S. Gu, S. Wang, L. Wenyin, and E. Chen, "Question recommendation for user-interactive question answering systems," in Proceedings of the 2nd international conference on Ubiquitous information management and communication, 2008, pp. 39-44.
[35] B. Li and I. King, "Routing questions to appropriate answerers in community question answering services," in Proceedings of the 19th ACM international conference on Information and knowledge management, 2010, pp.1585-1588.
[36] W.C. Kao, D.R. Liu, and S.W. Wang, "Expert finding in question-answering websites: a novel hybrid approach," in Proceedings of the ACM Symposium on Applied Computing, 2010, pp.867-871.
[37] F. Riahi, Z. Zolaktaf, M. Shafiei, and E. Milios, "Finding expert users in community question answering," in Proceedings of the 21st International Conference on World Wide Web, 2012, pp.791-798.
[38] L. Du, W. Buntine, and H. Jin, "A segmented topic model based on the two-parameter poisson-dirichlet process," Machine Learning, vol.81, pp. 5-19, 2010.
[39] M. Liu, Y. Liu, Q. Yang, "Predicting best answerers for new questions in community question answering," in Proceedings of 11th International Conference Web-Age Information Management, 2010, pp. 127-138.
[40] X. Liu, W.B. Croft, and M. Koll, "Finding experts in community-based question answering services," in Proceedings of the 14th ACM international conference on Information and knowledge management, 2005, pp. 315–316.
[41] J. Guo, S. Xu, S. Bao, and Y. Yu, "Tapping on the potential of Q&A community by recommending answer providers," in Proceedings of the 17th ACM conference on Information and knowledge management, 2008, pp. 921-930.
[42] H. Zhu, E. Chen, and H. Cao, "Finding experts in tag based knowledge sharing communities," in Proceedings of the 5th International Conference Knowledge Science Engineering and Management, 2011, pp. 183–195.
[43] C. Castro-Herrera, "A hybrid recommender system for finding relevant users in open source forums," in Proceedings of the 3rd International Workshop on Managing Requirements Knowledge, 2010, pp. 41–50.
[44] G. Dror, Y. Koren, Y. Maarek, and I. Szpektor, "I want to answer; who has a question? : Yahoo! answers recommender system," in Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining, 2011, pp. 1109-1117.
[45] J. H. Friedman, "Greedy function approximation: A gradient boosting machine," The Annals of Statistics, vol.29, pp.1189-1232, 2001.
[46] J. H. Friedman, "Stochastic gradient boosting," Computational Statistics & Data Analysis, vol.38, pp. 367–378, 2002.
[47] D. Horowitz and S.D. Kamvar, "The anatomy of a large-scale social search engine," in Proceedings of the 19th International Conference on World Wide Web, 2010, pp. 431–440.
[48] X. Li, J. Ma, Y. Yang, and D. Wang, "A Service Mode of Expert Finding in Social Network," in Proceedings of the International Conference on Service Sciences, 2013, pp. 220-223.
[49] E. Gabrilovich and S. Markovitch, "Computing semantic relatedness using Wikipedia-based explicit semantic analysis," in Proceedings of the 20th International Joint Conference on Artificial Intelligence, 2007, pp. 1606–1611.
[50] Z. Zhao, L. Zhang, X. He, and W. Ng, "Expert Finding for Question Answering via Graph Regularized Matrix Completion," IEEE Transactions on Knowledge and Data Engineering, vol.27, no.4, 993-1004, 2015.
[51] T. Hofmann, "Probabilistic latent semantic indexing," in Proceedings of the SIGIR, 1999, pp.51-52.
[52] H. Zhang, "The optimality of naive Bayes," in Proceedings of the 7th International Florida Artificial Intelligence Research Society Conference, 2004, pp. 562–567.
[53] Y. Koren, "Factorization meets the neighborhood: a multifaceted collaborative filtering model," in Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2008, pp.426–434.
[54] S. Rendle, "Factorization machines," in Proceedings of the International Conference on Data Mining, 2010.
[55] M. Zeidenberg, "Neural networks in artificial intelligence," in Ellis Horwood Limited, Glasgow, U.S., 1990.
[56] H. Guo, R. Tang, Y. Ye, Z. Li, and X. He, "Deep FM: A Factorization-Machine based Neural Network for CTR Prediction," in Proceedings of the 26th International Joint Conference on Artificial Intelligence, 2017, pp.1725–1731.
[57] S. Yuan, Y. Zhang, J. Tang, and W. Hall, J.B. Cabota, "Expert finding in community question answering: a review," Artificial Intelligence Review, pp.1–32, 2019.
[58] S. Wang, D. Jiang, L. Su, Z. Fan, and X. Liu, "Expert Finding in CQA Based on Topic Professional Level Model," International Conference on Data Mining and Big Data, 2018.
[59] Z. Liu and Y. Zhang, "Structures or Texts? A Dynamic Gating Method for Expert Finding in CQA Services," Database Systems for Advanced Applications, QLD, Australia, 2018.
[60] P.K. Roy, J.P. Singh, and A. Nag, "Finding Active Expert Users for Question Routing in Community Question Answering Sites," International Conference on Machine Learning and Data Mining in Pattern Recognition, NY, USA, 2018.
[61] A. Choudhary, H. Duhar, and E.S. Pilli, "Discovering Experts in Question Answering Community," in Proceedings of the 3rd International Conference and Workshops on Recent Advances and Innovations in Engineering (ICRAIE), 2018.
[62] A.D. Nobari, M. Neshati, and S.S. Gharebagh, "Quality-aware skill translation models for expert finding on StackOverflow," Information Systems, vol.87, 2020.
[63] P. Resnick, N. Iacovou, M. Suchak, P. Bergstrom, and J. Riedl, "GroupLens: an open architecture for collaborativefiltering of netnews," in Proceedings of the 1994 ACM Conference on ComputerSupported Cooperative Work, Minneapolis, U.S., 1994.
[64] P. Resnick, H.R. Varian, "Recommender systems," Communications of the ACM, vol. 40, pp. 56-58, 1997.
[65] S. Yuan, Y. Zhang, J. Tang, W. Hall, and J. B. Cabota, "Expert finding in community question answering: a review," Artificial Intelligence Review, pp. 1–32, 2019.
[66] S. Rendle, "Factorization machines," in Proceedings of the 10th IEEE International Conference on Data Mining, 2010, pp. 1-6.
[67] Y. Juan, Y. Zhuang, W.S. Chin, and C.J. Lin, "Field-aware factorization machines for CTR prediction," in Proceedings of the 10th ACM Conference on Recommender Systems, 2016, pp. 43-50.
[68] L. Hong, A.S. Doumith, and B.D. Davison, "Co-Factorization machines: Modeling user interests and predicting individual decisions in Twitter," in Proceedings of the sixth ACM international conference on Web search and data mining, 2013, pp. 557-566.
[69] H. Guo, R. Tang, Y. Ye, Z. Li, and X. He, "Deep FM: A factorization-machine based neural network for CTR prediction," in Proc. of the 26th Int'l Joint Conf. on Artificial Intelligence, 2017, pp. 1725-1731.
[70] H.T. Cheng et al., "Wide & deep learning for recommender systems," in Proc. of the 1st Workshop on Deep Learning for Recommender Systems, 2016, pp. 7-10.
[71] S. Bird, E. Klein, E. Loper, "Natural language processing with Python: analyzing text with the natural language toolkit," first ed., Gravenstein Highway North, Sebastopol, CA, 2009.
[72] J.L. Herlocker, J.A. Konstan, A. Borchers, J. Riedl, "An algorithmic framework for performing collaborative filtering," ACM SIGIR Forum, vol. 51, no.2, pp.227-234, July, 2017.
[73] S. Lin, W. Hong, D. Wang, and T. Li, "A survey on expert finding techniques," Journal of Intelligent Information Systems, pp.255-279, Feb., 2017.
[74] M. Rafiei and A.A. Kardan,"A novel method for expert finding in online communities based on concept map and PageRank," Human-centric computing and information sciences, 2015.
[75] Z. Zhao, F. Wei, M. Zhou, and W. Ng, "Cold-start expert finding in community question answering via graph regularization," International Conference on Database Systems for Advanced Applications, China, 2015.
[76] X. Liu, S. Ye, X. Li, Y. Luo, and Y. Rao, "Zhihurank: A topic-sensitive expert finding algorithm in community question answering websites," International Conference on Web-Based Learning, China, 2015.
[77] M. Dehghan and A.A. Abin, "Translations diversification for expert finding: A novel clustering-based approach," ACM Transactions on Knowledge Discovery from Data, vol. 13, no 3, pp. 32-52, May, 2019.
[78] V. Boeva, M. Angelova, and E. Tsiporkova, "Data-driven techniques for expert finding," in Proceedings of the 9th International Conference on Agents and Artificial Intelligence, 2017, pp. 535-542.
[79] F. Amato, G. Cozzolino, and G. Sperlì, "A hypergraph data model for expert-finding in multimedia social networks," Information, vol. 10, May, 2019.
[80] Z. Sun, L. Han, W. Huang and et al., "Recommender systems based on social networks," The Journal of Systems and Software, vol. 99, pp.109-119, Jan., 2015.
[81] 游軒甯。應用Aspect Model於社群問答網站中尋找專家之研究–以Quora為例。國立東華大學，花蓮縣。2016。