除了將推薦系統 (Recommendation Systems) 用於商業領域，其他類型的網站也有推薦系統的建立。隨著越來越多新穎社群媒體的出現，許多人由Facebook轉往使用其他社群平台，例如Instagram。過去研究大多針對單一網站的推薦機制進行探討。本研究以Facebook與Instagram為例，探討跨社群的個人化推薦(Personalized Recommendation)。
　　現有推薦方法大多是以使用者於網站中的歷史紀錄作為推薦依據。本研究的目的為，進行跨平台個人化推薦，以可能影響使用者喜好的因素建構模型，針對在目標平台中沒有歷史紀錄的新用戶提出新的推薦方法。本研究期望透過使用者於Facebook偏好的粉絲專頁，推測其成為Instagram新用戶時，可能會喜愛的照片。
　　本研究選擇數名Facebook使用者作為實驗對象，以問卷方式驗證本研究所提出的方法是否有效，問卷格式仿照Instagram的形式，以照片為主，再加上時間與文字內容，每位受測者共有20張照片可選擇，10張為本研究推薦與10張Instagram推薦給新用戶的照片。實驗結果顯示，本研究所提出的方法可成功推薦使用者有興趣的照片。

In addition to e-commerce, recommendation systems are also adopted on other types of websites. As there are more and more emerging social media, many people have switched from Facebook to other social websites, such as Instagram. Most existed recommendation systems are designed based on single website. In this study, we design a personalized recommendation system for utilizing data form different social media.
　　There are many recommendation methods, and most of them are based on historical data of users on a website. The purpose of this study is to generate personalized recommendations for a social media based on data form another. In this study, we propose a new recommendation method for new users who have no record in target social media but leave rich data in others. A user’s favorite fanpages on Facebook are used to recommend articles that he / she may like on Instagram.
　　Some Facebook users are selected as experimental subjects in this study, and questionnaires are used to verify the effective of proposed method. Experiment results showed that the proposed method worked, and experimental subjects were interested in the articles recommended by the proposed method.

目錄
致　謝	I
中文摘要	III
英文摘要	V
圖目錄	X
表目錄	XI
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	5
1.4	研究流程	6
第二章	文獻探討	8
2.1	社群媒體的轉變	8
2.1.1	Facebook	8
2.1.2	Instagram	9
2.2	推薦系統	12
2.2.1	協同過濾推薦	12
2.2.2	基於內容推薦	14
2.2.3	混合式推薦系統	14
2.2.4	小結	16
2.3	主題標籤	19
2.4	文字相似度	19
第三章	研究方法	21
3.1	資料收集	21
3.2	研究架構	21
3.3	模型建構	25
3.4	小結	27
第四章	實證分析	28
4.1	案例說明	28
4.1.1	實驗對象	29
4.1.2	實驗時間與情境	30
4.2	結果分析	32
第五章	結論與建議	35
5.1	結論	35
5.2	未來發展與建議	36
參考文獻	38
圖目錄
圖1-1 2016年應用程式使用量成長率	3
圖1-2 2016年應用程式使用時間成長率	3
圖1-3 本研究流程圖	7
圖2-1台灣最多人使用的前12大社群網站和通訊媒體	9
圖2-2 Facebook各年齡層使用狀況	10
圖3-1 研究架構	23
圖3-2刪減文字範例	24
圖4-1 本研究案例問卷呈現方式	31
圖4-2 Instagram推薦新使用者的照片	32
表目錄
表2-1 推薦方法相關文獻	16
表2-1 推薦方法相關文獻 (續1)	17
表2-1 推薦方法相關文獻 (續2)	18
表3-1 Facebook粉絲專頁名稱含有的標點符號	22
表4-1 本研究實驗結果	33

中文文獻
IT技術 (2017)。推薦系統常見的推薦方法。217年5月5日，取自https://www.itread01.com/articles/1493953036.html，擷取時間2017年5月8日。
IT技術 (2019)。文字相似度的那些演算法。2019年1月11日，取自https://www.itread01.com/content/1547192171.html，擷取時間2019年5月19日。
Naomi L (2018)。FB 社群龍頭地位不保？ 臺灣網路社群趨勢全分析。2018年4月15日，取自https://www.marketersgo.com/marketing/201804/2017-social-media-analysis-report/，擷取時間2019年5月13日。
中央社 (2018)。全球40億人上網 台灣網民佔88%平均日上網469分。2018年2月1日，取自https://newtalk.tw/news/view/2018-02-01/112848，擷取日期2019年5月9日。
何佩珊 (2017)。還好還有Instagram，研究顯示Facebook持續流失年輕族群。2017年8月23日，取自https://www.bnext.com.tw/article/45875/snapchat-beat-facebook-and-instagram-in-young-people-in-the-us，擷取時間2019年5月12日。
酷哥康 sir (2017)。App使用時間調查：社群類使用成長4成、新聞類使用衰退5%。2017年3月13日，取自https://www.smartm.com.tw/article/33323630cea3，擷取日期2019年5月7日。
英文文獻
Billsus, D., & Pazzani, M. J. (1998, July). Learning Collaborative Information Filters. In Icml (Vol. 98, pp. 46-54).
Cheung, C. M., & Lee, M. K. (2010). A theoretical model of intentional social action in online social networks. Decision support systems, 49(1), 24-30.
Cheung, C. M., Chiu, P. Y., & Lee, M. K. (2011). Online social networks: Why do students use facebook?. Computers in Human Behavior, 27(4), 1337-1343.
Hu, G. N., Dai, X. Y., Song, Y., Huang, S. J., & Chen, J. J. (2015, June). A synthetic approach for recommendation: combining ratings, social relations, and reviews. In Twenty-Fourth International Joint Conference on Artificial Intelligence.
Hu, Q., Zhang, R., and Zhou, Y. (2016). “Transfer learning for short-term wind speed prediction with deep neural networks.” Renewable Energy 85, pp. 83-95.
Herlocker, J. L., Konstan, J. A., & Riedl, J. (2000, December). Explaining collaborative filtering recommendations. In Proceedings of the 2000 ACM conference on Computer supported cooperative work (pp. 241-250). ACM.
Hatzlvassiloglou, V., Klavans, J. L., & Eskin, E. (1999). Detecting text similarity over short passages: Exploring linguistic feature combinations via machine learning. In 1999 Joint SIGDAT conference on empirical methods in natural language processing and very large corpora.
Joinson, A. N. (2008, April). Looking at, looking up or keeping up with people?: motives and use of facebook. In Proceedings of the SIGCHI conference on Human Factors in Computing Systems (pp. 1027-1036). ACM.
Kompan, M., & Bieliková, M. (2010, September). Content-based news recommendation. In International conference on electronic commerce and web technologies (pp. 61-72). Springer, Berlin, Heidelberg.
Koren, Y., Bell, R., & Volinsky, C. (2009). Matrix factorization techniques for recommender systems. Computer, (8), 30-37.
Lu, J., Behbood, V., Hao, P., Zuo, H., Xue, S., and Zhang, G. (2015). “Transfer Learning using computational intelligence: A survey.” Knowledge-Based Systems 80, pp. 14-23.
Li, Y. M., Wu, C. T., & Lai, C. Y. (2013). A social recommender mechanism for e-commerce: Combining similarity, trust, and relationship. Decision Support Systems, 55(3), 740-752.
Mcandrew, F. T., & Jeong, H. S. (2012). Who does what on Facebook? Age, sex, and relationship status as predictors of Facebook use. Computers in Human Behavior, 28(6), 2359-2365.
Mishne, G. (2006, May). Autotag: a collaborative approach to automated tag assignment for weblog posts. In Proceedings of the 15th international conference on World Wide Web (pp. 953-954). ACM.
Pazzani, M. J., & Billsus, D. (2007). Content-based recommendation systems. In The adaptive web (pp. 325-341). Springer, Berlin, Heidelberg.
Qian, X., Feng, H., Zhao, G., & Mei, T. (2014). Personalized recommendation combining user interest and social circle. IEEE transactions on knowledge and data engineering, 26(7), 1763-1777.
Ross, C., Orr, E. S., Sisic, M., Arseneault, J. M., Simmering, M. G., & Orr, R. R. (2009). Personality and motivations associated with Facebook use. Computers in human behavior, 25(2), 578-586.
Rowe, G., & Wright, G. (2001). Expert opinions in forecasting: the role of the Delphi technique. In Principles of forecasting (pp. 125-144). Springer, Boston, MA.
Resnick, P., & Varian, H. R. (1997). Recommender systems. Communications of the ACM, 40(3), 56-59.
Schafer, J. B., Konstan, J., & Riedl, J. (1999, November). Recommender systems in e-commerce. In Proceedings of the 1st ACM conference on Electronic commerce (pp. 158-166). ACM.
Sheldon, P., & Bryant, K. (2016). Instagram: Motives for its use and relationship to narcissism and contextual age. Computers in human Behavior, 58, 89-97.
Shambour, Q., & Lu, J. (2011). A hybrid trust‐enhanced collaborative filtering recommendation approach for personalized government‐to‐business e‐services. International Journal of Intelligent Systems, 26(9), 814-843.
Sun, Z., Han, L., Huang, W., Wang, X., Zeng, X., Wang, M., & Yan, H. (2015). Recommender systems based on social networks. Journal of Systems and Software, 99, 109-119.
Van Meteren, R., & Van Someren, M. (2000, May). Using content-based filtering for recommendation. In Proceedings of the Machine Learning in the New Information Age: MLnet/ECML2000 Workshop (pp. 47-56).
Wang, Y. F., Chuang, Y. L., Hsu, M. H., & Keh, H. C. (2004). A personalized recommender system for the cosmetic business. Expert Systems with Applications, 26(3), 427-434.
Zhang, Y., Baghirov, F., Hashim, H., & Murphy, J. (2016). Gender and instagram hashtags: A study of# malaysianfood. In Conference on Information and Communication Technologies in Tourism.