隨著網路的高速發展，網路無視距離的優勢提供世界各地大量的資料供使用者參考，也因此過濾出合適的資料是需要花上大量的時間與精力，為了避免這個問題，推薦系統是一個很理想的解決方法，而推薦系統也被大量應用在各個領域上，同樣地也有被使用在學術論文的領域上，本文發現在現存的論文中，鮮少有如何推薦初入該領域的研究人員適合的論文，對於初入新的領域的研究人員，他們對該領域的了解有限，如果研究人員能掌握研究領域演進的歷程以及往後延伸的技術，對於深入了解該領域會有很大的幫助，因此基於這個概念，本文希望通過改變現有的方法設計一套基於研究領域發展軌跡的論文推薦系統，能推薦使用者相關的論文幫助他們了解該領域的發展。

With the rapid development of the Internet, the advantage of the Internet regardless of distance provides a large amount of data around for user to refer. Therefore, it takes a lot of time and energy to filter out the right information. To avoid this problem, a recommendation system is an ideal solution. The recommendation systems are widely used in various fields, as well as in the field of academic paper. This article found that among the existing papers, few papers are recommended for researchers who are new to the field. For researchers who are new to a new field, their knowledge of the field is limited. If researchers can master the evolution of the research field and the technology that will be extended in the future, it will be of great help to understand the field in depth. Therefore, based on this concept, this article hopes to design a paper recommendation system based on the development trajectory of the research field by changing the existing methods which can recommend users related papers to help them understand the development of the field.

第一章 緒論　　1
1.1 研究背景　　1
1.2 研究動機與目的　　1
1.3 論文架構　　2
第二章 相關論文研究　　3
2.1 推薦系統　　3
2.2 序列式樣探勘　　4
2.3 文獻探討　　6
第三章 系統架構與推薦方法　　7
3.1 資料庫設計　　7
3.2 作者研究歷程模型　　8
3.3 關鍵字研究歷程模型　　9
3.4 論文排序　　12
第四章 實驗與評估　　14
4.1 實驗資料來源　　14
4.2 研究歷程模型建立時間　　14
4.3 實例　　15
4.4 作者研究歷程權重有無比較　　20
4.5 推薦系統滿意度掉查　　23
4.6 評估方法　　23
4.7 推薦系統滿意度調查實驗結果　　24
第五章 結論　　26
第六章 參考文獻　　27

[1] G. Linden, B. Smith and J. York, "Amazon.com recommendations: item-to-item collaborative filtering," in IEEE Internet Computing, vol. 7, no. 1, pp. 76-80, Jan.-Feb. 2003.
[2] Y. C. Yoon and J. W. Lee, "Movie Recommendation Using Metadata Based Word2Vec Algorithm," 2018 International Conference on Platform Technology and Service (PlatCon), Jeju, 2018, pp. 1-6.
[3] A. Patel and R. Wadhvani, "A Comparative Study of Music Recommendation Systems," 2018 IEEE International Students' Conference on Electrical, Electronics and Computer Science (SCEECS), Bhopal, 2018, pp. 1-4.
[4] Y. Sun, W. Ni and R. Men, "A Personalized Paper Recommendation Approach Based on Web Paper Mining and Reviewer's Interest Modeling," 2009 International Conference on Research Challenges in Computer Science, Shanghai, 2009, pp. 49-52.
[5] M. Lu, Z. Qu, M. Wang and Z. Qin, "Recommending authors and papers based on ACTTM community and bilayer citation network," in China Communications, vol. 15, no. 7, pp. 111-130, July 2018.
[6] Q. Gao and L. Xin, "Products recommend algorithm based on customer preference model and affective computing," Proceedings of the 29th Chinese Control Conference, Beijing, 2010, pp. 2981-2986.
[7] J. Ma and Y. Lu, "A recommend system for modelling large-scale advertising," International Conference on Cyberspace Technology (CCT 2014), Beijing, 2014, pp. 1-4.
[8] Yichen Jiang, Aixia Jia and Yansong Feng, "Recommending Academic Paper via Users’ Reading Purposes," Proceedings of the Sixth ACM Conference on Recommender System, pp.241-244, September 2012.
[9] Luam C. Totti, Prasenjit Mitra, Mourad Ouzzani, Mohammed J. Zaki, "A Query-oriented Approach for Relevance in Citation Networks," Proceedings of the 25th International Conference Companion on World Wide Web, pp.401-406, April 2016
[10] Guannan Zhao, Shijian Luo and Ji He, "Style matching model-based recommend system for online shopping," 2009 IEEE 10th International Conference on Computer-Aided Industrial Design & Conceptual Design, Wenzhou, 2009, pp. 1995-1999.
[11] Xingyuan Li, "Collaborative filtering recommendation algorithm based on cluster," Proceedings of 2011 International Conference on Computer Science and Network Technology, Harbin, 2011, pp. 2682-2685.
[12] 林士傑,“基於學術研究發展之論文推薦系統”, 國立東華大學資訊工程學系碩士論文,2018
[13] Arif E. Jinha, “Article 50 million: an estimate of the number of scholarly articles in existence,” LEARN PUBLISHING, July 1 2010
[14] M. D. Ekstrand, P. Kannan, J. A. Stemper, J. T. Butler, J. A. Konstan, and J. T. Riedl, “Automatically building research reading lists,” in Proceedings of the fourth ACM conference on Recommender systems, 2010.
[15]胡雅涵, 李彥賢, &林正賢, “結合社會性標籤及文獻內容於個人化學術文章推薦”, 國立中正大學資訊管理學系, 2015
[16] R. Agrawal, and R. Srikant, “Mining Sequential Pattern,” in Proceedings of International Conference on Data Engineering, 1995
[17] J. Han, J. Pei, B. Mortazavi-Asl, Q. Chen, U.Dayal, and M-C. Hsu, “FreeSpan: Frequent Pattern-projected Sequential Pattern Mining,” Proceedings of the Sixth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, MA, United States, 2000
[18] IEEE Xplore Digital Library. 檢自https://ieeexplore.ieee.org/Xplore/home.jsp (2020)
[19] Digital Bibliography & Library Project. 檢自https://dblp.uni-trier.de/statistics/publicationsperyear.html (June 1, 2020)
[20] Itread01，四種推薦系統原理介紹(基於內容過濾/協同過濾/關聯規則/序列模式)(2019)。檢自https://www.itread01.com/content/1549456226.html (April 5, 2020)