Mining long-term search history to improve search accuracy
- 20 August 2006
- conference paper
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 718-723
- https://doi.org/10.1145/1150402.1150493
Abstract
Long-term search history contains rich information about a user's search preferences, which can be used as search context to improve retrieval performance. In this paper, we study statistical language modeling based methods to mine contextual information from long-term search history and exploit it for a more accurate estimate of the query language model. Experiments on real web search data show that the algorithms are effective in improving search accuracy for both fresh and recurring queries. The best performance is achieved when using clickthrough data of past searches that are related to the current query.Keywords
This publication has 11 references indexed in Scilit:
- Implicit user modeling for personalized searchPublished by Association for Computing Machinery (ACM) ,2005
- UCAIRPublished by Association for Computing Machinery (ACM) ,2005
- Context-sensitive information retrieval using implicit feedbackPublished by Association for Computing Machinery (ACM) ,2005
- Adaptive web search based on user profile constructed without any effort from usersPublished by Association for Computing Machinery (ACM) ,2004
- Implicit feedback for inferring user preferenceACM SIGIR Forum, 2003
- Challenges in information retrieval and language modelingACM SIGIR Forum, 2003
- A taxonomy of web searchACM SIGIR Forum, 2002
- Optimizing search engines using clickthrough dataPublished by Association for Computing Machinery (ACM) ,2002
- Model-based feedback in the language modeling approach to information retrievalPublished by Association for Computing Machinery (ACM) ,2001
- A study of smoothing methods for language models applied to Ad Hoc information retrievalPublished by Association for Computing Machinery (ACM) ,2001