No search result left behind: branching behavior with browser tabs

Today's Web browsers allow users to open links in new windows or tabs. This action, which we call 'branching', is sometimes performed on search results when the user plans to eventually visit multiple results. We detect branching behavior on a large commercial search engine with a client-side script on the results page. Two-fifths of all users spawned new tabs on search results in the timeframe of our study; branching usage varied with different query types and vertical. Both branching and backtracking are viable methods for visiting multiple search results. To understand user search strategies, we treat multiple result clicks following a query as ordered events to understand user search strategies. Users branching in a query are more likely to click search results from top to bottom, while users who backtrack are less likely to do so; this is especially true for queries involving more than two clicks. These findings inform an experiment in which we take a popular click model and modify it to account for the differing user behavior when branching. By understanding that users continue examining search results before viewing a branched result, we can improve the click model for branching queries.

[1]  Zhihua Zhang,et al.  Learning click models via probit bayesian inference , 2010, CIKM.

[2]  Ryen W. White,et al.  Parallel browsing behavior on the web , 2010, HT '10.

[3]  Yuchen Zhang,et al.  Incorporating post-click behaviors into a click model , 2010, SIGIR.

[4]  Bonnie MacKay,et al.  Exploring multi-session web tasks , 2008, CHI.

[5]  Shengdong Zhao,et al.  Measuring web page revisitation in tabbed browsing , 2011, CHI.

[6]  D. Norman,et al.  Psychological Issues in Support of Multiple Activities , 1986 .

[7]  Thorsten Joachims,et al.  Accurately Interpreting Clickthrough Data as Implicit Feedback , 2017 .

[8]  Xiaolong Li,et al.  Inferring search behaviors using partially observable Markov (POM) model , 2010, WSDM '10.

[9]  Filippo Menczer,et al.  Agents, bookmarks and clicks: a topical model of web navigation , 2010, HT '10.

[10]  Benjamin Piwowarski,et al.  A user browsing model to predict search engine click data from past observations. , 2008, SIGIR '08.

[11]  Chao Liu,et al.  Click chain model in web search , 2009, WWW '09.

[12]  Kuansan Wang,et al.  Inferring search behaviors using partially observable markov model with duration (POMD) , 2011, WSDM '11.

[13]  Rosie Jones,et al.  Beyond the session timeout: automatic hierarchical segmentation of search topics in query logs , 2008, CIKM '08.

[14]  Ravi Kumar,et al.  Stochastic models for tabbed browsing , 2010, WWW '10.

[15]  Michal Skubacz,et al.  Relevance and Impact of Tabbed Browsing Behavior on Web Usage Mining , 2006, 2006 IEEE/WIC/ACM International Conference on Web Intelligence (WI 2006 Main Conference Proceedings)(WI'06).

[16]  Ahmed Hassan Awadallah,et al.  Beyond DCG: user behavior as a predictor of a successful search , 2010, WSDM '10.

[17]  Amanda Spink,et al.  Multitasking during Web search sessions , 2006, Inf. Process. Manag..

[18]  Eelco Herder,et al.  Not quite the average: An empirical study of Web use , 2008, TWEB.

[19]  Olivier Chapelle,et al.  A dynamic bayesian network click model for web search ranking , 2009, WWW '09.

[20]  Amanda Spink,et al.  How are we searching the World Wide Web? A comparison of nine search engine transaction logs , 2006, Inf. Process. Manag..

[21]  Mika Käki,et al.  Information search and re-access strategies of experienced web users , 2005, WWW '05.

[22]  Eelco Herder,et al.  Off the beaten tracks: exploring three aspects of web navigation , 2006, WWW '06.

[23]  Andrew Thatcher,et al.  Web search strategies: The influence of Web experience and task type , 2008, Inf. Process. Manag..

[24]  Nick Craswell,et al.  An experimental comparison of click position-bias models , 2008, WSDM '08.

[25]  Ravin Balakrishnan,et al.  A study of tabbed browsing among mozilla firefox users , 2010, CHI.