Automatic abstracting and indexing—survey and recommendations
Communications of the ACM
Information Retrieval
Adaptive web search based on user profile constructed without any effort from users
Proceedings of the 13th international conference on World Wide Web
Web-page classification through summarization
Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval
A large-scale evaluation and analysis of personalized search strategies
Proceedings of the 16th international conference on World Wide Web
Personalized web exploration with task models
Proceedings of the 17th international conference on World Wide Web
Automatic retrieval of similar content using search engine query interface
Proceedings of the 18th ACM conference on Information and knowledge management
The automatic creation of literature abstracts
IBM Journal of Research and Development
User profiles for personalized information access
The adaptive web
Personalized search on the world wide web
The adaptive web
Modern Information Retrieval
Normal distribution re-weighting for personalized web search
Canadian AI'11 Proceedings of the 24th Canadian conference on Advances in artificial intelligence
| Hi-index | 0.00 |
A fundamental problem with current Web search technology is that in the absence of any additional information, the same query provided by two different searchers will produce the same set of search results, even if the information needs of the searchers are different. Web search personalization has been proposed as a solution to this problem, whereby the interests and preferences of individual users are modelled and used to affect the outcomes of their subsequent searches. A common approach is to generate vector-based models of searchers' interests, and re-rank the search results based on the similarity of the documents to these models. In this paper, a novel approach is proposed to automatically identify and re-weight significant dimensions in vector-based models in order to improve the personalized order of Web search results. This approach is inspired by Luhn's model of term importance, which is rooted in Zipf's Laws. Evaluations with a set of ambiguous queries illustrate the effectiveness of this approach.