Personalized ranking has been widely discussed recently. While current search engines do a good job at delivering pages associated with query terms issued by users, individual user’s needs may be different even when the same query term is issued. Economists, researchers who have been interested in human search behaviors for a long time, have found that people have many considerations when making searches. People are likely to determine how an information valuable to them on their past search experiences. In this paper, we propose a method for estimating individual user’s Experience for the query term issued. Then, we present how search engines incorporate other considerations, such as Confidence and Novelty, into their ranking algorithms based on Experience. Our experimental results show that our method achieves a higher level of precision than other algorithms those take fewer considerations and variables into account.

搜尋引擎的主要功能就是幫使用者找到和他所下的查詢相關的資訊，並將結果依照相關程度排序，以幫助使用者快速找到自己想要的資訊。目前網路上的搜尋引擎都將這樣的技術發展到成熟的階段了，然而，即使所下的查詢一樣，使用者想要的資訊卻有可能因人而異，也因此最近幾年個人化搜尋的相關研究開始被廣泛的討論。經濟學者也是對人類搜尋行為相當有興趣的一群學者，他們認為人類搜尋行為相當複雜，對人類來說，資訊是有價值的，而人會根據自己過去的經驗跟現況，考慮許多因素，最後才決定一個資訊的價值，這個值也代表了使用者是否需要這個資訊。在本研究中，我們提出了一個方法來估算使用者過去的經驗，然後以此經驗值來調節使用者搜尋時的其他考量，如信心值跟資訊新穎度，進而推測每一個資訊對該使用者的價值為何，以此為每個使用者做個人化的排序，讓搜尋引擎回傳的結果可以更符合使用者的需求。實驗結果顯示比起其他不做個人化排序的方法，或是其他沒有考量其他因素的方法，我們的方法可以達到較高的準確度。

[1] Understanding user goals in web search. ACM Press, 2004.
[2] Personalized search based on user search histories, 2005.
[3] E. Agichtein, E. Brill, and S. Dumais. Improving web search ranking by incorporating user behavior information. In SIGIR’ 06: Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval, pages 19–26, 2006.
[4] A. Broder. A taxonomy of web search. SIGIR Forum, 36(2):3–10, 2002.
[5] J. Carbonell and J. Goldstein. The use of mmr, diversitybased reranking for reordering documents and producing summaries. In SIGIR’98: Proceedings of the 21st annual international ACM SIGIR conference on Research and development in information retrieval, pages 335–336, 1998.
[6] E. Gabrilovich, S. Dumais, and E. Horvitz. Newsjunkie: Providing personalized newsfeeds via analysis of information novelty, 2004.
[7] S. Gauch, J. Chaffee, and A. Pretschner. Ontology-based personalized search and browsing. Web Intelli. and Agent Sys., 1(3,4):219–234, 2003.

[8] B. J. Jansen, A. Spink, and T. Saracevic. Real life, real users, and real needs: a study and analysis of user queries on the web. Information Processing and Management, 36(2):207–227, 2000
[9] X. Li and B. W. Croft. Improving novelty detection for general topics using sentence level information patterns. In CIKM’06: Proceedings of the 15th ACM international conference on Information and knowledge management, pages 238–247, 2006.
[10] P. Lyman and H. R. Varian. How much information?
http://www2.sims.berkeley.edu/research/projects/how-much-info-2003/
[11] Netflix official website. http://www.netflix.com/.
[12] Netflix prize. http://www.netflixprize.com/.
[13] Personalization is over-rated.
http://www.useit.com/alertbox/981004.html.
[14] L. Page, S. Brin, R. Motwani, and T. Winograd. The pagerank citation ranking: Bringing order to the web. Technical report, Stanford Digital Library Technologies Project, 1998.
[15] A. Pretschner and S. Gauch. Ontology based personalized search. In ICTAI, pages 391–398, 1999.
[16] F. Qiu and J. Cho. Automatic identification of user interest for personalized search. In WWW’06: Proceedings of the 15th international conference on World Wide Web, pages 727–736, 2006.
[17] G. Salton and C. Buckley. Term-weighting approaches in automatic text retrieval. Inf. Process. Manage., 24(5):513–523, 1988.
[18] G. J. Stigler. The economics of information. The Journal of Political Economy, 69(3):213–225, 1961.
[19] J. Teevan, S. Dumais, and E. Horvitz. Beyond the commons: Investigating the value of personalizing web search, 2005.
[20] H. R. Varian. Economics and search. SIGIR Forum, 33(1):1–5, 1999.