Incorporating non-sequential behavior into click models
- Submitting institution
-
University of Nottingham, The
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1324653
- Type
- E - Conference contribution
- DOI
-
10.1145/2766462.2767712
- Title of conference / published proceedings
- SIGIR '15 Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval
- First page
- 283
- Volume
- 2015-August
- Issue
- -
- ISSN
- -
- Open access status
- -
- Month of publication
- August
- Year of publication
- 2015
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
5
- Research group(s)
-
-
- Citation count
- 22
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Inspired by eye-tracking experiments, this paper proposes an effective model that can incorporate implicit non-sequential user click behaviour on the search page, reliably predicting the relevance of a web page to a query. Without any expensive user labelling, this algorithm can learn to rank the web pages for any queries with users' click data. The model has been used by Sogou, the no.2 search engine in China and serves as one of the most important features for search ranking. The paper won the best honorable mention award at SIGIR'2015.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
