現在位置首頁 > 博碩士論文 > 詳目
論文中文名稱:基於重疊社群發現之服裝購物推薦系統 [以論文名稱查詢館藏系統]
論文英文名稱:An Apparel Shopping Recommender System Based on Overlapping Community Discovery [以論文名稱查詢館藏系統]
院校名稱:臺北科技大學
學院名稱:管理學院
系所名稱:資訊與財金管理系碩士班
畢業學年度:103
畢業學期:第二學期
中文姓名:唐子晴
英文姓名:Tzu-Ching Tang
研究生學號:102938015
學位類別:碩士
語文別:中文
口試日期:2015/07/08
指導教授中文名:翁頌舜
指導教授英文名:Sung-Shun Weng
口試委員中文名:林榮禾;吳瑞堯;楊欣哲
中文關鍵詞:重疊社群混合式推薦推薦系統
英文關鍵詞:Overlapping CommunityHybrid RecommendationsRecommendation Systems
論文中文摘要:隨著網際網路的興起、行動裝置的流行,促成行動商務的普及。在網路購物時,尤其是服裝類別的商品,面對琳瑯滿目的服裝時,對消費者來說經常是處於難以抉擇的情況。而眾多的資料在網路中產生,也加劇了分析上的困難。
因此本研究提出一個基於重疊社群發現的服裝購物推薦系統,利用重疊社群發現演算法,在不破壞網路結構的前提下,首先將眾多的使用者網路分群,在調節社群中閾值設於0.5時,有著較佳的分群品質。再利用協同過濾式推薦方法預測群集內的使用者評分,以及內容導向式推薦,進而改善資料稀疏性及冷啟動問題,最終以TOP-N之方式將服裝商品推薦給使用者。
本研究開發基於Android系統以及網頁版的服裝購物推薦App,根據受試者使用本系統後回饋的系統評估問卷進行分析,結果呈現本系統是有良好的操作性、易讀性以及推薦結果符合使用者偏好。
論文英文摘要:The rise of the Internet and the mobile devices has contributed to the popularity of mobile commerce. When online shopping, especially for apparel categories of products, we often have a difficult choice in facing with variety of products. Therefore, mass data are generated in the network, but it’s more difficult for the analysis.
Therefore, our study presents an apparel recommender system based on overlapping community discovery algorithm. First, we cluster the users on the network using overlapping community discovery algorithm without destroying the structure of the network. In the regulation of community, it will be a better modularity when the threshold is set at 0.5. Second, we use collaborative filtering recommendation as well as content-based recommendation to predict users’ ratings within the cluster. The two kinds of methods will improve the sparsity of data and clod start problem. Finally, we use the method of Top-N to recommend apparel products to users. Our study also developed an App of the apparel shopping recommender system in Android system and a website. According to the feedbacks of the subjects after using our system, the results presented in our study are that our system has good operability, legibility and the recommendation is accordance with users’ preference.
論文目次:摘 要 i
ABSTRACT ii
誌 謝 iii
目錄 iv
表目錄 vi
圖目錄 vii
第一章 緒論 1
1.1 研究背景與動機 1
1.2 研究目的 3
1.3 論文架構 4
第二章 文獻探討 5
2.1 社交網路(Social Network) 5
2.1.1 社群網路 (Community Network) 6
2.1.2 重疊社群 (Overlapping Community) 7
2.2 推薦系統(Recommender System) 10
2.2.1 內容導向式推薦(Content-based Recommendations) 11
2.2.2 協同過濾式推薦(Collaborative Filtering Recommendations) 12
2.2.3 混合式推薦(Hybrid Recommendations) 13
第三章 研究方法 15
3.1 系統架構 15
3.2 資料預處理 16
3.3 模組功能說明 17
3.3.1 資料驗證模組 17
3.3.2 偏好收集模組 18
3.3.3 分群模組 21
3.3.4 推薦模組 24
第四章 系統實作與實驗分析 31
4.1 實驗環境 31
4.1.1 實驗數據 32
4.1.2 基於中心節點重疊社群發現演算法閾值設定 34
4.2 服裝購物推薦系統展示 36
4.3 推薦系統評估方式 42
4.3.1 實驗結果分析 42
4.4 服裝推薦APP評估 45
第五章 結論 54
5.1 研究結論與貢獻 54
5.2 管理意涵 55
5.3 研究限制與未來展望 56
參考文獻 58
附錄 61
系統評估問卷 61
論文參考文獻:1. 科技產業資訊室,市場研究機構Gartner對2014年PC、平板與手機出貨量調查。http://iknow.stpi.narl.org.tw/post/Read.aspx?PostID=9869,2014。
2. MIC產業情報研究所,2013年行動購物調查。
http://mic.iii.org.tw/intelligence/pressroom/pop_pressFull.asp?sno=333&cred=2013%2F6%2F21,2013。
3. MIC產業情報研究所,2013年台灣網購行為。
http://mic.iii.org.tw/aisp/pressroom/press01_pop.asp?sno=353&%20&type1=2,2014。
4. 蘇怡仁、溫建成、陳岳群、許維麟,「以重疊社群分析引文網路支援論文自動分類之探討」,KC2012第八屆知識社群國際研討會,2012。
5. 許世宗,利用情境擷取及情境感知網路服務的智能購物環境,中華大學資訊工程所,碩士論文,新竹,2010。.
6. 莊清男,協同過濾式群體推薦,中央大學資訊管理研究所,碩士論文,桃園,2005。
7. 林揆棟,以相鄰群體尋找重疊社群於複雜網路之研究,碩士論文,樹德科技大學資訊工程研究所,高雄,2009。
8. 萬雪飛,基於社會網絡的協同過濾推薦技術研究,碩士論文,電子科技大學計算機軟件與理論,北京,2010。
9. 鍾博欽,情境式個人化穿著推薦系統,碩士論文,成功大學工程科學研究所,台南,2009。
10. 李佳馨,整合內容導向式方法與混合式協同過濾之電影推薦,碩士論文,台北科技大學資訊管理研究所,台北,2013。
11. 官思伍,結合情境資訊與適地性服務之餐廳推薦,碩士論文,台北科技大學資訊管理研究所,台北,2014。
12. Adomavicius, G., & Tuzhilin, A., “Toward the Next Generation of Recommender Systems: A Survey of the State-of-the-Art and Possible Extensions,” IEEE Transactions on Knowledge and Data Engineering, vol. 17, no 6, 2005, pp. 734-749.
13. Armstrong, R., Freitag, D., Joachims, T., & Mitchell, T. “Webwatcher: A learning apprentice for the world wide web, ” AAAI Spring Symposium on Information Gathering from Heterogeneous, Distributed Environments, 1975, pp. 6-12.
14. Ahn, H. J. “A new similarity measure for collaborative filtering to alleviate the new user cold-starting problem. Information Sciences,” Information Sciences, vol. 178, no 1, 2008, pp. 37-51.
15. Balabanovic, M. & Shohan, Y., “Fab: content-based, collaborative recommendation,” Communications of ACM, vol. 40, no. 3, 1997, pp. 66-72.
16. Burke, R. “Hybrid recommender systems: Survey and experiments,” User Modeling and User-Adapted Interaction, vol.12, no. 4 , 2002, pp. 331-370.
17. Breese, J. S. Heckerman, D. & Kadie, C. “Empirical Analysis of Predictive Algorithms for Collaborative Filtering,” In Proceedings of the 14th Conference on Uncertainty in Artificial Intelligence,1998, pp. 43-52.
18. Chung, K., Song, C., Rim, K., & Lee, J. “Quick response system using collaborative filtering on fashion E-business,” Computational collective intelligence. technologies and applications, 2010, pp. 54-63.
19. Corpet, F. “Nucleic Acids Research 16”, 1988, pp. 10881-10890.
20. Chakraborty, T., & Chakraborty, A. “OverCite: Finding overlapping communities in citation network.” In Advances in Social Networks Analysis and Mining (ASONAM), 2013 IEEE/ACM International Conference, 2013, pp. 1124-1131
21. DeLone, W. H. & McLean, E. R. “The DeLone and McLean Model of Information System Success: A Ten-Year Update,” Journal of Management Information Systems, 2003, Vol.19, no 4, pp. 9-30.
22. Gulbahce, N., & Sune L. “The art of community detection.” BioEssays, Vol. 30, no. 10, 2008, pp. 934-938.
23. Girvan, M. & Newman, M.E.J. “Community structure in social and biological networks,” Proceedings of the National Academy of Sciences, Vol. 99, 2002, pp. 7821–7826.
24. Gregory, S. “Finding overlapping communities in networks by label propagation” New Journal of Physics, Vol. 12, no 10, 2010, pp. 103018.
25. Haythornthwaite, C. “Social networks and internet connectivity effects,” Information, Community & Society, vol.8 ,no. 2, 2005, pp. 125-147.
26. Hartigan, J. A. “Clustering algorithms”, New York: John Wiley & Sons, 1975.
27. Herlocker, J. L., Konstan, J. A., Terveen, L. G., & Ried J. T. “Evaluating collaborative filtering recommender systems.”, ACM Transactions on Information Systems (TOIS), Vol. 22, no 1, 2004, pp. 5-53.
28. Jannach, D., Zanker, M., Felfernig, A. & Friedrich, G., “Recommender Systems An Introduction,” Cambridge: Cambridge University Press, 2010, pp. 51-79.
29. Krulwich, B., & Burkey, C. “The InfoFinder agent: Learning user interests through heuristic phrase extraction,” IEEE Intelligent Systems, vol 12, no 5, 1975, pp. 22-27.
30. Kim B. M., Li Q., Kim, S. G. & Kim, J. Y., “A New Approach for Combining Content-based and Collaborative Filters,” Journal of Intelligent Information Systems archive, vol. 27, no. 6, 2006, pp. 79-91
31. Lang, K. “Newsweeder: Learning to filter netnews,” In Proceedings of the Twelfth International Conference on Machine Learning, 1975.
32. Lee, C., Reid, F., McDaid, A., & Hurley, N. “Detecting highly overlapping community structure by greedy clique expansion.” Proceedings of the 4th International Workshop on Social Network Mining and Analysis, 2010, pp. 33-42.
33. Newman, M.E.J. “Modularity and community structure in networks”, Proceedings of the National Academy of Sciences, Vol. 109, No. 12, 2006, pp. 8577–8582.
34. Palla, G, Derenyi, I & Vicsek, T. “The Critical Point of k-Clique Percolation in the Erdos–Renyi Graph,” Journal of Statistical Physic, vol. 128, 2007, pp. 219–227.
35. Resnick, P., & Varian, H. R. “Recommender systems,” Communications of the ACM, vol.40, no 3, 1997, pp. 56-58.
36. Resnick, P., Iacovou, N., Suchak, M., Bergstrom, P., & Riedl, J. “GroupLens: An open architecture for collaborative filtering of netnews,” Proceedings of the 1994 ACM Conference on Computer Supported Cooperative Work, 1994, pp. 175-186.
37. Simmel, G. “Soziologie ,” Duncker & Humblot, 1908.
38. Tokatli, N. “Global sourcing: Insights from the global clothing industry—the case of zara, a fast fashion retailer”, Journal of Economic Geography, 2007, lbm035.
39. Videla-Cavieres, I. F., & Ríos, S. A, “ Extending market basket analysis with graph mining techniques: A real case,” Expert Systems with Applications, Vol 41, no. 4, 2014, pp. 1928-1936.
40. Xue, G., Lin, C., Yang, Q., Xi, W., Zeng, H., Yu, Y., et al. “Scalable collaborative filtering using cluster-based smoothing,” Proceedings of the 28th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 2005, pp. 114-121.
論文全文使用權限:同意授權於2020-07-29起公開