Using Intent Information to Model User Behavior in Diversified Search

Chuklin, Aleksandr; Serdyukov, Pavel; Rijke, Maarten de

doi:10.1007/978-3-642-36973-5_1

Cited by 32 publications

(25 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These include the personalized click model [30], the task-centric click model [37], intent-aware modifications of UBM and DBN [9], the federated click models [6], the vertical-aware click model [33], the content-aware click model [34], and noise-aware modifications of UBM and DBN [7].…”

Section: Click Modelsmentioning

confidence: 99%

“…Figure 6 plots the t-SNE projections of the vector state s7 for different distances to the previous click. 9 Here, we compute the vector states for the query sessions in Sa, and then filter out some vector states to construct a balanced set that contains equal number of vector states for each distance d = 0, 1, . .…”

Section: Concepts Learned By Ncmmentioning

confidence: 99%

“…The subspaces of vector states sr for ranks r > 3 have large overlaps with each other. We hypothesize that this is due to the fact that other 9 We choose s7 because the rank 7 is low enough to see a sufficient number of distances but not too low to suffer from sparsity. …”

Section: Concepts Learned By Ncmmentioning

confidence: 99%

See 2 more Smart Citations

A Neural Click Model for Web Search

Borisov

Markov

Rijke

et al. 2016

Proceedings of the 25th International Conference on World Wide Web

Self Cite

134

121

View full text Add to dashboard Cite

A neural click model for web searchBorisov, A.; Markov, I.; de Rijke, M.; Serdyukov, P. General rightsIt is not permitted to download or to forward/distribute the text or part of it without the consent of the author(s) and/or copyright holder(s), other than for strictly personal, individual use, unless the work is under an open content license (like Creative Commons). Disclaimer/Complaints regulationsIf you believe that digital publication of certain material infringes any of your rights or (privacy) interests, please let the Library know, stating your reasons. In case of a legitimate complaint, the Library will make the material inaccessible and/or remove it from the website. Please Ask the Library: http://uba.uva.nl/en/contact, or a letter to: Library of the University of Amsterdam, Secretariat, Singel 425, 1012 WP Amsterdam, The Netherlands. You will be contacted as soon as possible. ABSTRACTUnderstanding user browsing behavior in web search is key to improving web search effectiveness. Many click models have been proposed to explain or predict user clicks on search engine results. They are based on the probabilistic graphical model (PGM) framework, in which user behavior is represented as a sequence of observable and hidden events. The PGM framework provides a mathematically solid way to reason about a set of events given some information about other events. But the structure of the dependencies between the events has to be set manually. Different click models use different hand-crafted sets of dependencies.We propose an alternative based on the idea of distributed representations: to represent the user's information need and the information available to the user with a vector state. The components of the vector state are learned to represent concepts that are useful for modeling user behavior. And user behavior is modeled as a sequence of vector states associated with a query session: the vector state is initialized with a query, and then iteratively updated based on information about interactions with the search engine results. This approach allows us to directly understand user browsing behavior from click-through data, i.e., without the need for a predefined set of rules as is customary for PGM-based click models.We illustrate our approach using a set of neural click models. Our experimental results show that the neural click model that uses the same training data as traditional PGM-based click models, has better performance on the click prediction task (i.e., predicting user click on search engine results) and the relevance prediction task (i.e., ranking documents by their relevance to a query). An analysis of the best performing neural click model shows that it learns similar concepts to those used in traditional click models, and that it also learns other concepts that cannot be designed manually.

show abstract

Section: Click Modelsmentioning

confidence: 99%

Section: Concepts Learned By Ncmmentioning

confidence: 99%

See 1 more Smart Citation

A Neural Click Model for Web Search

Borisov

Markov

Rijke

et al. 2016

Proceedings of the 25th International Conference on World Wide Web

Self Cite

134

121

View full text Add to dashboard Cite

show abstract

“…Recently, it has been shown that patterns of user click behaviour can be learned automatically from interaction data [6]. In addition to position bias, recent work examines other types of bias including(i) vertical bias driven by visually salient vertical results (e.g., image results, video results, news results) [11,12,43]; (ii) query bias, which occurs if a query does not match the user's information need [45], (iii) duplicate bias, which occurs if a result has been examined earlier in the search task [45]; and (iv) bias driven by individual differences between users [40].…”

Section: Models Of User Behaviormentioning

confidence: 99%

A Context-aware Time Model for Web Search

Borisov

Markov

Rijke

et al. 2016

Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval

Self Cite

View full text Add to dashboard Cite

A context-aware time model for web search Borisov, A.; Markov, I.; de Rijke, M.; Serdyukov, P. General rightsIt is not permitted to download or to forward/distribute the text or part of it without the consent of the author(s) and/or copyright holder(s), other than for strictly personal, individual use, unless the work is under an open content license (like Creative Commons). Disclaimer/Complaints regulationsIf you believe that digital publication of certain material infringes any of your rights or (privacy) interests, please let the Library know, stating your reasons. In case of a legitimate complaint, the Library will make the material inaccessible and/or remove it from the website. Please Ask the Library: http://uba.uva.nl/en/contact, or a letter to: Library of the University of Amsterdam, Secretariat, Singel 425, 1012 WP Amsterdam, The Netherlands. You will be contacted as soon as possible. ABSTRACTIn web search, information about times between user actions has been shown to be a good indicator of users' satisfaction with the search results. Existing work uses the mean values of the observed times, or fits probability distributions to the observed times. This implies a context-independence assumption that the time elapsed between a pair of user actions does not depend on the context, in which the first action takes place. We validate this assumption using logs of a commercial web search engine and discover that it does not always hold. For between 37% to 80% of queryresult pairs, depending on the number of observations, the distributions of click dwell times have statistically significant differences in query sessions for which a given result (i) is the first item to be clicked and (ii) is not the first. To account for this context bias effect, we propose a context-aware time model (CATM). The CATM allows us(i) to predict times between user actions in contexts, in which these actions were not observed, and (ii) to compute contextindependent estimates of the times by predicting them in predefined contexts. Our experimental results show that the CATM provides better means than existing methods to predict and interpret times between user actions.

show abstract

“…I will highlight progress on the interface of these areas by focusing on three examples. In the first, I focus on result pages containing fresh results and propose a way to model user intent distribution and bias due to different document presentation types [1]. In the second, I focus on the fresh vertical prediction task for repeating queries and address the following algorithmic problem: how to quickly and accurately detect fresh intent shifts and adjust the ranking in an online setting [3].…”

Section: Recent Advancesmentioning

confidence: 99%