現在位置首頁 > 博碩士論文 > 詳目
論文中文名稱:結合意見分析之情境式推薦系統以數位相機為例 [以論文名稱查詢館藏系統]
論文英文名稱:The Binding Opinion Analysis of Context Recommendation System: A Case Study of Digital Camera [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:范愷芸
英文姓名:Kan-Yun Fan
研究生學號:102938014
學位類別:碩士
語文別:中文
口試日期:2015/06/12
指導教授中文名:王貞淑
指導教授英文名:Chen-Shu Wang
口試委員中文名:丁一賢;蕭文龍
中文關鍵詞:推薦系統情境意見分析
英文關鍵詞:Recommendation SystemContextOpinion Analysis
論文中文摘要:網路上的資訊琳瑯滿目,龐大資訊會造成資訊超載,導致使用者不易找到符合需求的資訊。而推薦系統的出現就是為了解決資訊超載,能幫助使用者快速找到符合的資訊進而達到推薦的效果。目前多數的推薦系統其情境考量多應用於偵測週遭環境,非考量使用者對於使用產品的時機而進行個人化推薦。故本研究添加使用者的使用情境、大眾的評論與評分,將以上三項目列為考量因素之一,推薦整體分數較高的產品型號給予使用者做參考依據。
本研究所設計的情境式推薦系統,其後端資料以網路爬蟲方式取得需要的資訊。產品評論資訊需要先斷詞才能進行意見分析,意見分析主要目的為審查文章中正、負面的意見。藉由使用者的使用情境,系統能推薦合適的產品,讓使用者免於花費大量時間研究各產品功能所代表之意義,最後由受測者給予排名,分析系統排名與受測者的排名之差異,排名結果利用距離公式與交換次數,計算其準確率。透過實驗結果知,本研究推薦產品的結果準確率為七成九五,意指系統所推薦的產品是有符合使用者的使用情境,未來期望能將此情境式推薦系統應用於不同類型之產品。
論文英文摘要:A lot of information on the Internet will cause information overloading, which makes the user spending many time to find the information that meets their needs. The emergence of the recommendation systems is to solve the problem of information overloading. Because recommendation system comes with special mechanisms, it can help users quickly to find information. Therefore, it can recommend products to user. At present, most of the recommendation systems use context-aware for detecting the environment and didn’t consider users’ usage situation. The study designs a new recommendation system, adding usage situation and product reviews and scores which rated by public. Finally, system will recommend products which meet the user needs. The priority of recommended order is according to the overall score.
The study design the context recommendation system which data use the way of web crawler to obtain information. The information of review must be hyphenated to carry out opinion analysis. Opinion analyzes the main purpose is determined the review article which is positive or negative. By consideration of users’ usage situation, system will recommend suitable products, so user can avoid to spend a lot of time to study the meanings of each product functions. Finally, user give us the ranking and we analyze the differences of systems ranking and user ranking. To calculate its accuracy, we use the concept of distance formula and swap times. According to experimental results, the results of this study shows the accuracy rate that is 79.5%, meaning that the system recommend products can meet the users' usage. In the future, the context recommendation system can be applied to different types of products.
論文目次:中文摘要 i
英文摘要 ii
誌謝 iv
目錄 v
表目錄 vii
圖目錄 viii
第一章 緒論 1
1.1研究動機與背景 1
1.2研究目的 2
1.3研究架構 3
1.4研究範圍與限制 4
第二章 文獻探討 5
2.1 推薦系統 5
2.1.1 內容導向式推薦系統 6
2.1.2 協同過濾式推薦系統 7
2.1.3 混合式推薦系統 10
2.2 情境處理 11
2.3 中文斷詞系統 13
2.4 意見分析 15
第三章 研究方法 18
3.1 系統架構 18
3.2 資料後端的前處理 19
3.3 情境處理模組 25
3.4 推薦與回饋模組 28
第四章 系統實作與實驗分析 32
4.1 系統環境 32
4.2 實驗方法與系統說明 32
4.3 評估方法 38
4.3.1 距離公式(MAE) 38
4.3.2 交換(Swap)次數 38
4.4 樣本特徵分析 42
4.4 實驗結果 44
4.4.1 情境一 44
4.4.2 情境二 46
4.4.3 情境三 48
4.4.4 情境四 50
4.4.5 小結 52
第五章 結論與未來展望 53
5.1 結論 54
5.2 未來研究方向 55
參考文獻 56
附錄
A 前測問卷 60
論文參考文獻:[1] 莊清男,協同過濾式群體推薦,碩士論文,中央大學資訊管理研究所,桃園,2005
[2] 蕭朝維,應用情境感知及模糊理論於智慧型推薦系統,碩士論文,朝陽科技大學資訊管理研究所,臺中,2012
[3] 鍾博欽,情境式個人化穿著推薦系統,碩士論文,國立成功大學工程科學研究所,臺南,2009
[4] 黃文奇、吳世弘、陳良圃、谷圳,「中文文字蘊涵系統之特徵分析」,自然語言與語音處理研討會,台北,2011,第281-296頁。
[5] 孫瑛澤、陳建良、劉峻杰、劉昭麟、蘇豐文,「中文短句之情緒分類」,自然語言與語音處理研討會,南投暨南大學,2010,第184-198頁。
[6] 趙妍研、秦兵、劉挺,文本情感分析,Journal of Software, vol.21, no.8, Aug.2010, pp.1834−1848
[7] 李啟菁,中文部落格文章之意見分析,碩士論文,國立臺北科技大學資訊工程研究所,臺北,2010。
[8] 簡之文,部落格文章情感分析之研究,碩士論文,私立淡江大學資訊管理學系,臺北,2012
[9] 鄭帆評,運用動態屬性之商品推薦方法-以數位相機為例,碩士論文,私立銘傳大學資訊管理學系,桃園,2013。
[10] Linden. G., Smith. B. and York. J, "Amazon.com Recommendation : Item-to-Item Collaborative filtering," Journal of IEEE Internet Computing, Vol.7, Jan/Feb.2003, pp. 76-80.
[11] Miller, B. N., Albert, I., Lam, S. K., Konstan, J. A., and Riedl, J., "MovieLens unplugged: experiences with an occasionally connected recommender system," In Proceedings of the 8th ACM international conference on Intelligent user interfaces , 2003, pp. 263-266.
[12] Liang, T. P., Lai, H. J., and Ku, Y. C., "Personalized content recommendation and user satisfaction: Theoretical synthesis and empirical findings, " Journal of Management Information Systems , vol. 23, 2006, pp. 45-70.
[13] Schafe, J. B., Konstan, J and Riedl. J., "Recommender systems in e-commerce," Proceedings of the 1st ACM conference on Electronic commerce, 1999, pp. 158-166.
[14] Resnick, Paul, and Hal R. Varian. "Recommender systems." Communications of the ACM , vol.40, no. 3, 1997, pp. 56-58.
[15] Kim, B. M., Li, Q., Park, C. S., Kim, S. G., and Kim, J. Y., "A new approach for combining content-based and collaborative filters, " Journal of Intelligent Information Systems, vol.27, no. 1, 2006, pp. 79-91.
[16] Goldberg, D., Nichols, D., Oki, B. M., and Terry, D., "Using collaborative filtering to weave an information tapestry," Communications of the ACM, vol.35, no.12, 1992, pp. 61-70.
[17] Rashid, A. M., Albert, I., Cosley, D., Lam, S. K., McNee, S. M., Konstan, J. A., and Riedl, J., "Getting to know you: learning new user preferences in recommender systems, " In Proceedings of the 7th international conference on Intelligent user interfaces , Jan.2002, pp. 27-134.
[18] Wright S., "Personalisation: How a computer can know you better than yourself, " Multimedia Systems Conference, UK: Hampshire, 2002.
[19] Jia, Z., Yang, Y., Gao, W., and Chen, X. (2015, February), "User-Based Collaborative Filtering for Tourist Attraction Recommendations, " In: Computational Intelligence & Communication Technology (CICT), 2015 IEEE International Conference on. IEEE, 2015, pp. 22-25.
[20] RONG Hui-gui, HUO Sheng-xu, HU Chun-hua and MO Jin-xia, "User similarity-based collaborative filtering recommendation algorithm, " Journal on Communications, vol. 35, no. 2, February 2014, pp.16-24.
[21] Balabanović, M.,and Shohom,Y., "Content-Based, Callaborative Recommendation, " Communications of the ACM, vol.40, no.3, 1997.
[22] Burke. R, "Hybrid Recommender System : Survey and Experiment, " User Model.User Adapt.Inter., vol. 12, 2002, pp. 331-370.
[23] Soares, M., and Viana, P., "TV Recommendation and Personalization Systems: integrating broadcast and video on-demand services, " Advances in Electrical and Computer Engineering, vol. 1, 2014.
[24] Porter, M. E., Competitive advantage, New York: Free Press , 1985.
[25] Russel. W. Belk, "Situational Variables and Consumer Behavior, " Journal of Consumer Research, vol. 2, no. 3, Dec.1975.
[26] Wells, W. D. and Prensky, D., Consumer Behavior, New York, NY: John Wiley and Sons Inc., 1996.
[27] James F. Engel, David T. Kollat and Roger D. Blackwell , Consumer behavior, New York, Holt, Rinehart and Winston, Dem.1968.
[28] Hasen, R. A., and Deutscher, T., "An empirical investigation of attribute importance in retail store selection, " Journal of Retailing , vol. 53, no. 4, 1972, pp. 59-72.
[29] Engel, J. F., R. D. Blackwell, and P. W. Miniard , Consumer Behavior, 7th ed. Fort Worth, Dryden Press, 1993, pp. 53.
[30] Sappelli, Maya, Suzan Verberne, and Wessel Kraaij, "Recommending personalized touristic sights using Google Places," Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval. ACM, 2013.
[31] Do, P., Le, H., Nguyen, V. T., and Dung, T. N., "StudyAdvisor: A Context-Aware Recommendation Application in e-Learning Environment, " In Advanced Approaches to Intelligent Information and Database Systems .Springer International Publishing, 2014, pp. 119-128.
[32] Lommatzsch, Andreas, "Real-time news recommendation using context-aware ensembles," Advances in Information Retrieval. Springer International Publishing, 2014, pp. 51-62.
[33] Hu, Minqing, and Liu, Bing , "Mining and summarizing customer reviews, " In Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining , Aug. 2004, pp. 168-177.
[34] Chen, Chih-Ming. M., Tsai, M. F., Liu, J. Y., and Yang, Y. H., "Using emotional context from article for contextual music recommendation, " In Proceedings of the 21st ACM international conference on Multimedia, Oct. 2013, pp. 649-652.
[35] Zhang, Y., Zhang, M., Liu, Y., and Ma, S., "Incorporating Phrase-level Sentiment Analysis on Textual Reviews for Personalized Recommendation, " Proceedings of the Eighth ACM International Conference on Web Search and Data Mining, 2015.
[36] ACM.Hair, J. F., Anderson, R. E. , Tatham, R. L. , and Black, W. C., Multivariate Data Analysis, (5th ed.) Prentice-Hall, Inc., New Jersey, 1998.
論文全文使用權限:同意授權於2018-07-14起公開