臺灣博碩士論文加值系統

在科技發達的今日，無所不在的情境感知服務(Context-Aware Services)逐漸的成為新的趨勢。然而，要提供個人化的推薦，勢必要有充分的資訊及良好的推論模型(Inference Models)，因此，本研究提出應用情境感知及模糊理論於智慧型推薦系統，藉由情境感知(Context-Awareness)的概念來獲取使用者週遭的情境資訊(Contextual Information)，接著透過模糊推論引擎(Fuzzy Inference Engine)將專家的經驗結合到推論當中，藉此達到個人化的推薦。
此外，本研究也以個人化的廣告推薦為例，從使用者的交談內容及個人資訊中來蒐集短期和長期的情境資訊，並且利用這些情境資訊經由模糊推論引擎找出符合使用者需求的廣告，藉此發展一個具有個人化廣告特色的交談平台。最後，由本論文的實驗結果顯示，本研究所出的個人化廣告推薦確實能夠改善傳統廣告的點閱率，如此將可讓廣告主獲得良好的廣告效益，也能讓使用者取得感興趣的廣告，最後創造使用者及廣告主雙贏的局面。

Nowadays, the information technology is developed by leaps and bound. The ubiquitous context-awareness services have become new trends. Both sufficient information and good inference model are very important to obtain an effective recommendation. So, we propose a smart recommender system which integrates the technologies of context-awareness and fuzzy set theory. We employ the context-awareness technology to perceive the contextual information around. And, take the advantages of fuzzy set theory to combine the experiences of experts for the inference engine. Thus, the smart personal recommendation can be achieved. In our experiment, we extract the conversation contents of users in a conversation platform to obtain short-term contextual information and use the personal information of users to be long-term contextual information. We employ these contextual information to find the advertisements by fuzzy inference system. Finally, through the experiment results which we can improve the click rate of advertisement. Therefore, the advertisers can acquire more effective advertising and the user can also acquire advertisements which he like.

第1章緒論...............................................................................................1
1.1 研究背景與動機.......................................................................1
1.2 研究目的...................................................................................4
1.3 論文架構...................................................................................5
第2章文獻探討.......................................................................................6
2.1 情境感知(Context-Awareness)................................................6
2.2 模糊集合理論(Fuzzy Set Theory)...........................................9
2.3 網路廣告(Display Adverting)................................................11
2.4 知識本體(Ontology)...............................................................13
2.5 案例式推理(Case-Base Reasoning, CBR)............................17
第3章研究方法.....................................................................................20
3.1 研究架構.................................................................................20
3.2 個人化廣告推薦系統(Personal Advertising Recommender System)....................................................................................21
3.2.1 交談話題相似度(Topic Similarity, TS)..........................22
3.2.2 廣告熱門相似度(Hot Advertising Similarity, HAS)....27
3.2.3 個人偏好相似度(Personal Interest Similarity, PIS)....28
3.2.4 廣告案例相似度(Advertising Case Similarity, ACS)...30
3.2.5 模糊推論引擎(Fuzzy Inference Engine).......................31
3.3 實例說明.................................................................................35
第4章實驗.............................................................................................40
4.1 實驗環境.................................................................................40
4.2 專家知識本體之建置.............................................................40
4.3 系統介面.................................................................................41
4.4 實驗設計.................................................................................42
4.5 實驗結果與分析.....................................................................44
第5章結論與未來研究.........................................................................48
參考文獻.....................................................................................................49
附錄
中研院平衡語料庫詞類標記集[17]...................................................55

圖目錄
圖 1 豆豆聊天室的隨機廣告[19] ....................................................... 2
圖 2 網頁服務需求分析[45] .............................................................. 7
圖 3 COBRA 之架構[25] .................................................................... 8
圖 4 模糊推論系統之架構[46] ........................................................ 10
圖 5 2007-2010 台灣網路廣告成長趨勢[18]................................... 13
圖 6 知識本體之舉例....................................................................... 14
圖 7 Yahoo! Directory[55] ................................................................. 16
圖 8 案例式推理之循環圖[20] ........................................................ 17
圖 9 研究架構圖............................................................................... 21
圖 10 廣告推薦流程圖..................................................................... 22
圖 11 前置處理之流程..................................................................... 23
圖 12 購物領域之專家知識本體..................................................... 26
圖 13 專家知識本體的概念延伸之舉例......................................... 27
圖 14 個人化知識本體之運作流程................................................. 28
圖 15 偏好度更新之舉例.................................................................. 29
圖 16 案例式推理之舉例.................................................................. 31
圖 17 四種情境資訊相似度的模糊歸屬函數................................. 32
圖 18 使用者的個人化知識本體..................................................... 37
圖 19 專家知識本體轉換成資料庫的格式...................................... 40
圖 20 系統首頁................................................................................. 41
圖 21 交談平台................................................................................. 42
圖 22 廣告資料庫之部分廣告......................................................... 43
圖 23 調整過後的歸屬函數............................................................. 44
圖 24 斷詞之誤判(列舉) .................................................................. 45
圖 25 廣告點閱率之改善結果......................................................... 47

表目錄
表 1 詞彙重組規則[40] .................................................................... 24
表 2 重要詞性對照表[5] .................................................................. 25
表 3 本研究所定義的模糊規則....................................................... 33
表 4 廣告的熱門相似度................................................................... 36
表 5 廣告與過去案例的情境資訊相似度....................................... 37
表 6 廣告所對應的情境資訊相似度............................................... 39
表 7 廣告的情境資訊在高相似的歸屬程度................................... 39
表 8 實驗數據................................................................................... 46

[1]吳柏諺(2008)，以案例式推理為基礎之高速公路上危險事件預測系統，碩士論文，國立台灣師範大學資訊工程系，台北。
[2]林建宏(2006)，正規化概念分析建構電腦病毒特徵之知識本體，碩士論文，國立雲林科技大學資訊管理系，雲林。
[3]周郁菁(2008)，在時間限制下，網路廣告促銷方式對網路衝動性購買行為影響之研究，碩士論文，朝陽科技大學企業管理系，台中。
[4]俞帛宏(2009)，橫幅廣告點擊效果影響因素之探索性研究，碩士論文，國立臺北大學資訊管理系，台北。
[5]陳慶龍(2006)，可供語意搜尋之部分知識建構，碩士論文，國立成功大學工程科學系，台南。
[6]
莊清男(2005)，協同過濾式群體推薦，碩士論文，國立中央大學資訊管理系，桃園。
[7]翁頌舜，陳文典(2006)，整合情境資訊之多維度推薦環境，電子商務與數位生活研討會論文集，台北，光碟。
[8]許正欣(2004)，語意網上自動建構本體論之研究，碩士論文，碩士論文，天主教輔仁大學資訊管理學系，台北。
[9]張清雅(2010)，從金手指網路廣告獎探討台灣網路廣告設計之演變，國立臺灣藝術大學視覺傳達設計學系研究所碩士論文，台北。
[10]邱俊耀(2011)，本體論結合多準則權重運算之推薦系統以糖尿病藥物為例，碩士論文，朝陽科技大學資訊管理系，台中。
[11]辜樹仁(2006)，2006年力用全球-點閱率騙局，廣告主小心了，天下雜誌，357期。
[12]莊政翰(2007)，運用類神經網路與貝氏網路結合TF-IDF與Entropy特徵於本體論之自動建構，碩士論文，朝陽科技大學資訊管理系，台中。
[13]詹國良(2002)，案例式推理於企業信用評等決策之輔助應用，碩士論文，國立成功大學工業管理科學系，台南。
[14]溫瑞烘(2008)，植基於本體論之語意式工作媒合系統之研究，碩士論文，國立臺灣師範大學工業教育學系，台北。
[15]蔡旺典(2007)，建立個人化知識本體來輔助網頁行為探勘 – 以個人化網頁排序為例，碩士論文，朝陽科技大學資訊管理系，台中。
[16]中文斷詞系統(CKIP)，http://ckipsvr.iis.sinica.edu.tw/，2011/11/11。
[17]台北市網際網路廣告暨媒體經營協會，http://www.iama.org.tw/， 2011/8/20。
[18]豆豆聊天室，http://doo.idv.tw/, 2011/10/5。
[19]A. Aamodt and E. Plaza(1994), “Case-Based Reasoning: Foundational Issues, Methodological Variations, and System Approaches,” AI Communications. IOS Press, Vol. 7, No. 3, pp. 39-59.
[20]G. Bilchev and D. Marston(2003), “Personalised Advertising – Exploiting the Distributed User Profile,” BT Technology, Vol. 21, No. 1, pp. 84-90.
[21]R. Burke(2002), “Hybrid Recommender Systems: Survey and Experiments,” UserModelling and User-Adapted Interaction, Vol. 12, No. 4, pp. 331-370.
[22]D. J. Carmichael, J. Kay, and B. Kummerfeld(2004), “Personal Ontologies for Feature Selection in Intelligent Environment Visualisations,” Proceedings of the Workshop on Artificial Intelligence in Mobile Systems, pp. 44-51.
[23]J. Chaffee and S. Gauch(2000), “Personal Ontologies for Web Navigation,” Proceedings of the 9th International Conference on Information Knowledge Management (CIKM), pp. 227-234.
[24]H. Chen, T. Finin, A. Joshi, L. Kagal, F. Perich and, D. Chakraborty(2004), “Intelligent Agents Meet the Semantic Web in Smart Spaces,” IEEE Internet Computing, Vol. 8, No. 6, pp. 69-79.
[25]G. Chen and D. Kotz(2000), “A Survey of Context-Aware Mobile Computing Research” Technical Report Dartmouth Computer Science Technical Report TR2000-381, pp 1-16.
[26]J. Deane and M. Pathak(2009), “Ontological Analysis of Web Surf History to Maximize the Click-through Probability of Web Advertisements,” Decision Support Systems, Vol. 47, No. 4, pp. 364-373.
[27]M. Degemmis, P. Lops, and G. Semeraro(2007), “A content-Collaborative Recommender that Exploits WordNet-Based User Profiles for Neighborhood Formation,” User Modeling and User-Adapted Interaction, Vol. 17, No. 3, pp. 217-255.
[28]A. K. Dey(2001), “Understanding and Using Context,” Personal and Ubiquitous Computing, Special issue on Situated Interaction and Ubiquitous Computing, Vol. 5, No. 1, pp. 4-7.
[29]J. Garofalakis and T. Giannakoudi(2009), “Exploiting Ontologies for Web Search Personalization,” Web Personalization in Intelligent Environments, Vol. 229, pp. 49-54.
[30]T. R. Gruber(1993), “A Translation Approach to Portable Ontology Specifications,” IEEE Trans. on Rob., Vol. 14, No. 3, pp. 199-220.
[31]G. Gupta and W. C. Lee(2010), “Collaborative Spatial Object Recommendation in Location Based Services,” Proceedings of the 2010 39th International Conference on Parallel Processing Workshops, pp. 24-33.
[32]P. L. Hsu, P. C. Liu, and Y. S. Chen(2006), “Using Ontology to Map Categories in Blog,” AIDM ''06 Proceedings of the International Workshop on on Integrating AI and Data Mining, pp. 65-72.
[33]H. C. Huang, M. S. Lin and H. H. Chen(2008), “Analysis of Intention in Dialogues Using Category Trees and Its Application to Advertisement Recommendation,” The Third International joint conference on Natural Language Processing, pp. 625-630.
[34]M. N. Huhns and L. M. Stephens(1999), “Personal Ontologies,” Internet Computing, IEEE, Vol. 3, No. 5, pp. 85-87.
[35]Y. Jang, T. Lee, K. Kim, and W. Lee(2007), “Keyword Management System based on Ontology for Contextual Advertising,” Proceedings of the Sixth International Conference on Advanced Language Processing and Web Information Technology, pp. 440-445.
[36]M. Kayaalp, T. Ozyer, and S. T. Ozyer(2009), “A Collaborative and Content Based Event Recommendation System Integrated With Data Collection Scrapers and Services at a Social Networking Site,” Proceedings of the 2009 International Conference on Advances in Social Network Analysis and Mining, pp. 113-118.
[37]P. Kazienko and M. Adamski(2007), “AdROSA–Adaptive Personalization of Web Advertising,” Information Sciences, Vol. 177, No.11, pp. 2269-2295.
[38]J. H. Kim, K. Y. Chung, J. K. Ryu, K. W. Rim, and J. H. Lee(2008), “A Recommendation Agent System Using HMM-Based Collaborative Filtering in Smart Home Environment,” Proceedings of the Third International Conference on Convergence and Hybrid Information Technology, pp. 14-217.
[39]C. W. Lee, C. W. Shih, M. Y. Day, T. H. Tsai, T. J. Jiang, C. W. Wu, C. L. Sung, Y. R. Chen, S. H. Wu, and W. L. Hsu(2005), “ASQA: Academia Sinica Question Answering System for NTCIR-5 CLQA,” Proceedings of the NTCIR-5 Workshop Tokyo, pp. 202-208.
[40]S. C. Liao, K. F. Kao, I. E. Liao, H. L. Chen, and S. O. Huang(2009), "PORE: A Personal Ontology Recommender System for Digital Libraries", Electronic Library, Vol. 27, No 3, pp. 496-508.
[41]E. H. Mamdani(1977), “Application of Fuzzy Logic to Approximate Reasoning Using Linguistic Synthesis,” IEEE Trans. Computers, Vol.26, No.12, pp.1182-1191.
[42]S. E. Middleton, D. D. Roure, and N. R. Shadbolt(2009), “Ontology-Based Recommender Systems,” International Handbooks on Information Systems, Vol. 6, pp 4779-796.
[43]C. Porcel, A. G. L’opez-Herrera, and E. Herrera-Viedma(2009), “A Recommender System for Research Resources Based on Fuzzy Linguistic Modeling,” Expert Syst. Appl., Vol. 36, pp. 5173-5183.
[44]W. Rong and K. Liu(2010), “A Survey of Context Aware Web Service Discovery: From User’s Perspective,” 2010 Fifth IEEE International Symposium on Service Oriented System Engineering, pp. 15-22.
[45]J. Sargolzaei and M. Khoshnoodi(2008), “Fuzzy Inference System to Modeling of Cross Flow Milk Ultrafiltration,” Applied Soft Computing, Vo. 8, No. 1, pp 456-465.
[46]R. C. Schank(1982), “Dynamic Memory: A Theory of Reminding and Learning in Computers and People,” Cambridge University Press.
[47]B. Schilit, N. Adams, and Roy Want(1994), “Context-Aware Computing Applications,” Proceedings of IEEE Workshop on Mobile Computing Systems and Applications, pp 85-90.
[48]B. Schilit and M. Theimer(1994), “Disseminating Active Map Information to Mobile Hosts,” IEEE Network, Vol. 8, No. 5, pp. 22-32
[49]T. Takagi and M. Sugeno(1985), “Fuzzy Identification of Systems and Its Application to Modeling and Control,” IEEE Trans. Systems, Man, and Cybernetics, Vol. 15, No. 1, pp. 116-132.
[50]H. Ye(2011), “A Personalized Collaborative Filtering Recommendation Using Association Rules Mining and Self-Organizing Map,” Journal of Software, Vol. 6, No. 4, pp. 732-739.
[51]L. A. Zadeh(1965), “Fuzzy Sets,” Information and Control Vol. 8, No. 3, pp. 338-353.
[52]L. A. Zadeh(1973), “Outline of a New Approach to Analysis of Complex Systems,” IEEE Trans. on Sys. Man and Cyb, Vol. 1, No.1, pp. 28-44.
[53]Open Directory Project, http://www.dmoz.org/, 2011/10/5.
[54]Yahoo! Directory, http://tw.dir.yahoo.com/, 2011/10/15.