Enabling direct interest-aware audience selection

Advertisers typically have a fairly accurate idea of the interests of their target audience. However, today's online advertising systems are unable to leverage this information. The reasons are two-fold. First, there is no agreed upon vocabulary of interests for advertisers and advertising systems to communicate. More importantly, advertising systems lack a mechanism for mapping users to the interest vocabulary. In this paper, we tackle both problems. We present a system for direct interest-aware audience selection. This system takes the query histories of search engine users as input, extracts their interests, and describes them with interpretable labels. The labels are not drawn from a predefined taxonomy, but rather dynamically generated from the query histories, and are thus easy for the advertisers to interpret and use for targeting users. In addition, the system enables seamless addition of interest labels that may be provided by the advertiser.

[1]  Evgeniy Gabrilovich,et al.  Retrieval models for audience selection in display advertising , 2011, CIKM '11.

[2]  Olfa Nasraoui,et al.  Mining search engine query logs for query recommendation , 2006, WWW '06.

[3]  Filip Radlinski,et al.  Query chains: learning to rank from implicit feedback , 2005, KDD '05.

[4]  Lu Wang,et al.  Clustering query refinements by user intent , 2010, WWW '10.

[5]  Daqing He,et al.  Combining evidence for automatic Web session identification , 2002, Inf. Process. Manag..

[6]  Matthew Richardson,et al.  Learning about the world through long-term query logs , 2008, TWEB.

[7]  Aristides Gionis,et al.  The query-flow graph: model and applications , 2008, CIKM '08.

[8]  Sandeep Pandey,et al.  Learning to target: what works for behavioral targeting , 2011, CIKM '11.

[9]  Foster Provost,et al.  Audience selection for on-line brand advertising: privacy-friendly social network targeting , 2009, KDD.

[10]  Wen Zhang,et al.  How much can behavioral targeting help online advertising? , 2009, WWW '09.

[11]  Ryen W. White,et al.  Modeling and analysis of cross-session search tasks , 2011, SIGIR.

[12]  Patrick Pantel,et al.  Discovering word senses from text , 2002, KDD.

[13]  Lei Tang,et al.  Large-scale behavioral targeting with a social twist , 2011, CIKM '11.

[14]  John F. Canny,et al.  Large-scale behavioral targeting , 2009, KDD.

[15]  Marcin Sydow,et al.  Behavioural Targeting in On-Line Advertising: An Empirical Study , 2008, WISE.

[16]  Benjamin Piwowarski,et al.  Mining user web search activity with layered bayesian networks or how to capture a click in its context , 2009, WSDM '09.

[17]  Ravi Kumar,et al.  An analysis framework for search sequences , 2009, CIKM.

[18]  Kenneth Ward Church,et al.  Word Association Norms, Mutual Information, and Lexicography , 1989, ACL.

[19]  James E. Pitkow,et al.  Characterizing Browsing Strategies in the World-Wide Web , 1995, Comput. Networks ISDN Syst..

[20]  Alexander J. Smola,et al.  Scalable distributed inference of dynamic user interests for behavioral targeting , 2011, KDD.

[21]  Lise Getoor,et al.  Organizing User Search Histories , 2012, IEEE Transactions on Knowledge and Data Engineering.

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

[23]  Rong Yan,et al.  Social influence in social advertising: evidence from field experiments , 2012, EC '12.