學術產出-Theses
Article View/Open
Publication Export
-
題名 以使用者意見提升推薦系統效能之研究
Exploiting User Opinions for Improving Individual Recommendations作者 林金永 貢獻者 蔡銘峰
林金永關鍵詞 推薦系統
協同過濾
文字探勘
Recommender Systems
Collaborative Filtering
Text Mining
Factorization Machines日期 2016 上傳時間 2-Sep-2016 01:32:47 (UTC+8) 摘要 近年來,受惠於網路的盛行及其帶來的便利性,許多網站得以收集到大量的使用者對於商品之評價以及評論,運用這些使用者的回饋資料進行分析,以更精準的進行商業行銷正是當今浪潮。而推薦系統廣泛應用於商業行銷,常用的推薦系統之計算理論,乃依據使用者對商品的評分進行協同式的過濾,以找出合適的產品給予推薦,其理論的基礎是品味相近的消費者應該會喜歡類似的商品,使用者對商品的評分即為此模式所採用的依據,例如:運用User-based Collaborative Filtering,可以找出與被推薦者的特徵值類似的使用者,並以類似使用者中較高評分的項目作為推薦清單,這種方式能得到相當不錯的推薦結果,且計算的運算量亦不太大。相較之下,以使用者對商品的文字評論作為依據的推薦方法則較為少見,但我們認為文字訊息在推薦系統中亦佔有相當份量的重要性;直覺上,將使用者的評分與其文字評論作結合進行分析,應可更完整呈現該使用者的意向,並進而應能改進推薦系統之推薦效能。在這份論文研究中,我們嘗試結合使用者對商品的評分與文字評論於推薦系統中,並以一份取自TripAdvisor.com的使用者對於飯店評價之資料集進行實驗,透過libFM 建立推薦模型;從實驗結果探討中印證了我們的想法:使用者的文字評論訊息的確能夠用以改進推薦系統之效能。 參考文獻 [1] G. Adomavicius and Y. Kwon. New recommendation techniques formulticriteria rating systems. IEEE Intelligent Systems, 22(3):48–55,2007.[2] H. Ahn, K. Kim, and I. Han. Mobile advertisement recommender systemusing collaborative filtering: Mar-cf. 2006.[3] D. Bridge and A. Waugh. Using experience on the read/write web:The ghostwriter system. In Proceedings of WebCBR: The Workshopon Reasoning from Experiences on the Web (Workshop Programme ofthe Eighth International Conference on Case-Based Reasoning), pages15–24, 2009.[4] R. Burke. Hybrid recommender systems: Survey and experiments. Usermodeling and user-adapted interaction, 12(4):331–370, 2002.[5] M. Claypool, A. Gokhale, T. Miranda, P. Murnikov, D. Netes, andM. Sartin. Combining content-based and collaborative filters in an onlinenewspaper. In Proceedings of ACM SIGIR Workshop on RecommenderSystems, volume 60. Citeseer, 1999.[6] M. Fuchs and M. Zanker. Multi-criteria ratings for recommender systems:an empirical analysis in the tourism domain. In InternationalConference on Electronic Commerce and Web Technologies, pages100–111. Springer, 2012.[7] K. Ganesan and C. Zhai. Opinion-based entity ranking. InformationRetrieval, 15(2):116–150, 2012.33[8] G. Huming and L. Weili. A hotel recommendation system based oncollaborative filtering and rankboost algorithm. In 2010 second internationalconference on multimedia and information technology, 2010.[9] A. Levi, O. Mokryn, C. Diot, and N. Taft. Finding a needle in a haystackof reviews: cold start context-based hotel recommender system. In Proceedingsof the sixth ACM conference on Recommender systems, pages115–122. ACM, 2012.[10] Y. Liu, X. Huang, A. An, and X. Yu. Modeling and predicting thehelpfulness of online reviews. In Data Mining, 2008. ICDM’08. EighthIEEE International Conference on, pages 443–452. IEEE, 2008.[11] C. D. Manning, P. Raghavan, and H. Sch¨utze. Introduction to InformationRetrieval. Cambridge University Press, New York, NY, USA,2008.[12] M. P. O’Mahony and B. Smyth. Learning to recommend helpful hotelreviews. In Proceedings of the Third ACM Conference on RecommenderSystems, pages 305–308. ACM, 2009.[13] S. Rendle. Factorization machines. In Proceedings of Data Mining,2010 IEEE 10th International Conference on, pages 995–1000. IEEE,2010.[14] S. Rendle. Factorization machines with libFM. ACM Transactions onIntelligent Systems and Technology, 3(3):57:1–57:22, May 2012.[15] G. Salton, A. Wong, and C.-S. Yang. A vector space model for automaticindexing. Communications of the ACM, 18(11):613–620, 1975.[16] B. Sarwar, G. Karypis, J. Konstan, and J. Riedl. Item-based collaborativefiltering recommendation algorithms. In Proceedings of the 10thInternatio 描述 碩士
國立政治大學
資訊科學系碩士在職專班
101971019資料來源 http://thesis.lib.nccu.edu.tw/record/#G0101971019 資料類型 thesis dc.contributor.advisor 蔡銘峰 zh_TW dc.contributor.author (Authors) 林金永 zh_TW dc.creator (作者) 林金永 zh_TW dc.date (日期) 2016 en_US dc.date.accessioned 2-Sep-2016 01:32:47 (UTC+8) - dc.date.available 2-Sep-2016 01:32:47 (UTC+8) - dc.date.issued (上傳時間) 2-Sep-2016 01:32:47 (UTC+8) - dc.identifier (Other Identifiers) G0101971019 en_US dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/101253 - dc.description (描述) 碩士 zh_TW dc.description (描述) 國立政治大學 zh_TW dc.description (描述) 資訊科學系碩士在職專班 zh_TW dc.description (描述) 101971019 zh_TW dc.description.abstract (摘要) 近年來,受惠於網路的盛行及其帶來的便利性,許多網站得以收集到大量的使用者對於商品之評價以及評論,運用這些使用者的回饋資料進行分析,以更精準的進行商業行銷正是當今浪潮。而推薦系統廣泛應用於商業行銷,常用的推薦系統之計算理論,乃依據使用者對商品的評分進行協同式的過濾,以找出合適的產品給予推薦,其理論的基礎是品味相近的消費者應該會喜歡類似的商品,使用者對商品的評分即為此模式所採用的依據,例如:運用User-based Collaborative Filtering,可以找出與被推薦者的特徵值類似的使用者,並以類似使用者中較高評分的項目作為推薦清單,這種方式能得到相當不錯的推薦結果,且計算的運算量亦不太大。相較之下,以使用者對商品的文字評論作為依據的推薦方法則較為少見,但我們認為文字訊息在推薦系統中亦佔有相當份量的重要性;直覺上,將使用者的評分與其文字評論作結合進行分析,應可更完整呈現該使用者的意向,並進而應能改進推薦系統之推薦效能。在這份論文研究中,我們嘗試結合使用者對商品的評分與文字評論於推薦系統中,並以一份取自TripAdvisor.com的使用者對於飯店評價之資料集進行實驗,透過libFM 建立推薦模型;從實驗結果探討中印證了我們的想法:使用者的文字評論訊息的確能夠用以改進推薦系統之效能。 zh_TW dc.description.tableofcontents 1 Introduction 12 Related Work 52.1 文字探勘(Text Mining) 52.2 協同過濾(Collaborative Filtering) 72.2.1 以使用者為基礎(User-based)的協同過濾 82.2.2 以項目為基礎(Item-based)的協同過濾 92.2.3 以模型為基礎(Model-based)的協同過濾 102.3 基於內容的過濾(Content-Based Filtering) 102.4 混合式推薦系統(Hybrid Recommender Systems) 112.5 飯店推薦的相關研究工作 123 Methodology 153.1 分解機器函式庫(Factorization Machine Library) 153.2 資料集與文字前處理(Datasets and Preprocessing steps) 183.2.1 資料集 183.2.2 使用者對飯店評分的分布情形 193.2.3 文字前處理 193.2.4 文字評論資料集統計 214 Experimental Results 234.1 評量指標(Evaluation Metrics) 234.2 實驗設定(Experimental Settings) 244.2.1 實驗程序(Experimental Procedure) 264.3 實驗結果(Experimental Results) 274.3.1 libFM Regression實驗結果 274.3.2 libFM Binary Classification實驗結果 284.4 討論與分析(Discusssion and Analysis) 295 Conclusions and Future work 31 zh_TW dc.format.extent 1115837 bytes - dc.format.mimetype application/pdf - dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0101971019 en_US dc.subject (關鍵詞) 推薦系統 zh_TW dc.subject (關鍵詞) 協同過濾 zh_TW dc.subject (關鍵詞) 文字探勘 zh_TW dc.subject (關鍵詞) Recommender Systems en_US dc.subject (關鍵詞) Collaborative Filtering en_US dc.subject (關鍵詞) Text Mining en_US dc.subject (關鍵詞) Factorization Machines en_US dc.title (題名) 以使用者意見提升推薦系統效能之研究 zh_TW dc.title (題名) Exploiting User Opinions for Improving Individual Recommendations en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) [1] G. Adomavicius and Y. Kwon. New recommendation techniques formulticriteria rating systems. IEEE Intelligent Systems, 22(3):48–55,2007.[2] H. Ahn, K. Kim, and I. Han. Mobile advertisement recommender systemusing collaborative filtering: Mar-cf. 2006.[3] D. Bridge and A. Waugh. Using experience on the read/write web:The ghostwriter system. In Proceedings of WebCBR: The Workshopon Reasoning from Experiences on the Web (Workshop Programme ofthe Eighth International Conference on Case-Based Reasoning), pages15–24, 2009.[4] R. Burke. Hybrid recommender systems: Survey and experiments. Usermodeling and user-adapted interaction, 12(4):331–370, 2002.[5] M. Claypool, A. Gokhale, T. Miranda, P. Murnikov, D. Netes, andM. Sartin. Combining content-based and collaborative filters in an onlinenewspaper. In Proceedings of ACM SIGIR Workshop on RecommenderSystems, volume 60. Citeseer, 1999.[6] M. Fuchs and M. Zanker. Multi-criteria ratings for recommender systems:an empirical analysis in the tourism domain. In InternationalConference on Electronic Commerce and Web Technologies, pages100–111. Springer, 2012.[7] K. Ganesan and C. Zhai. Opinion-based entity ranking. InformationRetrieval, 15(2):116–150, 2012.33[8] G. Huming and L. Weili. A hotel recommendation system based oncollaborative filtering and rankboost algorithm. In 2010 second internationalconference on multimedia and information technology, 2010.[9] A. Levi, O. Mokryn, C. Diot, and N. Taft. Finding a needle in a haystackof reviews: cold start context-based hotel recommender system. In Proceedingsof the sixth ACM conference on Recommender systems, pages115–122. ACM, 2012.[10] Y. Liu, X. Huang, A. An, and X. Yu. Modeling and predicting thehelpfulness of online reviews. In Data Mining, 2008. ICDM’08. EighthIEEE International Conference on, pages 443–452. IEEE, 2008.[11] C. D. Manning, P. Raghavan, and H. Sch¨utze. Introduction to InformationRetrieval. Cambridge University Press, New York, NY, USA,2008.[12] M. P. O’Mahony and B. Smyth. Learning to recommend helpful hotelreviews. In Proceedings of the Third ACM Conference on RecommenderSystems, pages 305–308. ACM, 2009.[13] S. Rendle. Factorization machines. In Proceedings of Data Mining,2010 IEEE 10th International Conference on, pages 995–1000. IEEE,2010.[14] S. Rendle. Factorization machines with libFM. ACM Transactions onIntelligent Systems and Technology, 3(3):57:1–57:22, May 2012.[15] G. Salton, A. Wong, and C.-S. Yang. A vector space model for automaticindexing. Communications of the ACM, 18(11):613–620, 1975.[16] B. Sarwar, G. Karypis, J. Konstan, and J. Riedl. Item-based collaborativefiltering recommendation algorithms. In Proceedings of the 10thInternatio zh_TW