基於使用者行為之網頁推薦系統

如果現今網際網路看成是資料庫，那可以說是資料量與資料提供者皆最多的資料庫，那麼如何去挖掘這麼龐大的資料庫，已經是近幾年來的熱門研究議題，然而如何在廣大的資料庫中推薦給使用者合適的網頁，在推薦演算法相關研究中的內容導向或是協同過濾，都各有其缺點。本論文主要目的為探討如何結合避免內容導向以及協同過濾的缺點，卻又能達到相似的推薦效果，並且藉由分群演算法來改善以往推薦演算法因為使用者及推薦項目的增加，讓推薦計算的時間呈倍數成長的缺點。在本研究中，利用了瀏覽器工具列來搜集使用者瀏覽網路的資訊，並且透過工具列所記錄的使用者資訊，分析使用者的瀏覽行為，找出使用者的查詢關鍵字，利用查詢關鍵字透過搜尋引擎將相關網址找回，藉此建立關鍵字之間的相似度，以及擴展推薦系統的推薦項目，利用使用者的查詢關鍵字來建立使用者特徵向量，將使用者分群，再透過協同過濾的方法計算出該群組的推薦網頁，將網頁推薦給使用者。

關鍵字

內容過濾；協同過濾；推薦系統

並列摘要

This paper aims to explore how to combine content-oriented and avoid the shortcomings of collaborative filtering, it can achieve results similar to the recommendation. Because of hived off the clustering algorithms to improve the previous recommendation algorithms because users of the project and recommended an increase for the time recommended a multiple of calculating the growth of shortcomings. In this research, using a browser toolbar users to browse the Internet to collect the information and tools out through the records of user information. Toolbar through the records of user information, analysis of the user's browsing identify a user's query keywords. Through the use of keywords for search engine will find related url. Takes advantage of this between the establishment key words the similarity, and the expansion of the recommendation system recommended projects. Use of a user's query keywords to create a user eigenvector users Grouping. Penetrates the coordination filtration again the method of calculation to the group's recommendation page, the page will be recommended to the user.

並列關鍵字

Content-based Filtering ； Collaborative Filtering ； Recommendation System

參考文獻

[2] Adomavicius, G. and 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.

[3] Balabanovic, M. and Shoham, Y., “Fab: Content-based, Collaborative Recommendation,” Communications of the ACM, Vol. 40, No.3, 1997, pp. 66-72.

[4] Niu, L., Yan, X. W., Zhang, C. Q. and Zhang, S. C., “Product Hierarchy-based Customer Profiles for Electronic Commerce Recommendation,” Proceedings of the First International Conference on Machine Learning and Cybernetics, Beijing, 2002, pp. 1075-1080.

[6] Linden, G., Smith, B., and York, J., “Amazon.com Recommendations Item to Item Collaborative Filtering,” IEEE Internet Computing, Vol. 7, No. 1, 2003, pp. 76-80.

[8] Open Directory Project (ODP). http://www.dmoz.org

國際替代計量

基於使用者行為之網頁推薦系統

全文下載

主題瀏覽