Incremental relevance feedback for information filtering
SIGIR '96 Proceedings of the 19th annual international ACM SIGIR conference on Research and development in information retrieval
Efficient and effective metasearch for text databases incorporating linkages among documents
SIGMOD '01 Proceedings of the 2001 ACM SIGMOD international conference on Management of data
Optimizing search engines using clickthrough data
Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining
Personalized Web Search For Improving Retrieval Effectiveness
IEEE Transactions on Knowledge and Data Engineering
Accurately interpreting clickthrough data as implicit feedback
Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval
Mining User preference using Spy voting for search engine personalization
ACM Transactions on Internet Technology (TOIT)
Hi-index | 0.00 |
Search engines have been one of the most popular ways for people to find web pages of interest. Presently, when a user enters a keyword in a search engine, the search results are usually presented the same result to other users who search the same keyword, which might not be related to each user's field of interest. Therefore, the researcher of this study would like to propose a new searching technique to get each user's most relevant information by using a user preference. This research will categorize user preference to build the user profile and general profile base on user's search history and category hierarchy, respectively. The search engines then use those profiles to determine the interests of each user, execute the search query to obtain a set of relevant documents, and reranking the documents in a manner that best reflects their relevance to the user's profile. Many algorithms have been designed, analyzed, implemented and experimented to find the most appropriate and the most effective one to create the relationship between each keyword and each category to best meet each user's preference.