Aleksandr Chuklin of COMMIT/program INFINITI (Information Retrieval for Information Services) won the Best Student Paper Award at the 35th European Conference on Information Retrieval for a paper entitled "Using Intent Information to Model User Behavior in Diversified Search".
Aleksandr and INFINITI project leader Maarten de Rijke work together in a joint project with Yandex, the leading Russian search engine.
A result page of a modern commercial search engine often contains documents of different types targeted to satisfy different user intents (news, blogs, multimedia). When evaluating system performance and making design decisions we need to better understand user behaviour on such result pages. To address this problem various click models have previously been proposed. In this paper we focus on result pages containing fresh results and propose a way to model user intent distribution and bias due to different document presentation types. To the best of our knowledge this is the first work that successfully uses intent and layout information to improve existing click models.
The PDF of the paper can be found here below.