Balancing On-site Engagement

Abstract

Encouraging broader engagement with a target publisher's content by balancing on-site topic engagement. Responsive to receiving notification of a recipient's request of an item of content from the target publisher, the on-site and off-site content consumption history of the recipient is analyzed. For each of a plurality of topics, historic engagement with on-site and off-site content is measured. Deficient topics having better off-site engagement than on-site engagement are detected. Content comprising links to items of content available from the target publisher which are characterized by deficient topics is selected and sent to the recipient. In an embodiment, the supplemental content comprises a plurality of links to other web pages on the target publisher's website which are sent to the recipient browser before the requested item of content finishes loading.

What is claimed is: 
     
         1 . A computer-implemented method comprising:
 receiving notification of a browser's request of a web page of a target website, the target website comprising a plurality of web pages, each web page having an on-site topic and each on-site topic having an on-site topic strength; and   responsive to receiving the notification, sending supplemental content to the browser before the web page finishes loading by:
 measuring the browser's on-site engagement with each of a plurality of topics according to visits by the browser to a plurality of web pages of the target website and according to the on-site topic strength of the corresponding on-site topic of each of the plurality of web pages of the target website, wherein the plurality of web pages of the target website operate in a first domain controlled by a first business entity; 
 measuring the browser's off-site engagement with each of the plurality of topics according to visits by the browser to a plurality of off-site web pages, wherein the plurality of off-site web-pages operate in a second domain controlled by a second business entity, each of the plurality of off-site web pages having an off-site topic corresponding to one of the plurality of topics; and 
 determining an engagement gap corresponding to each of the plurality of topics by subtracting the corresponding measured on-site engagement from the corresponding measured off-site engagement; 
 identifying deficient topics, wherein a deficient topic has a positive engagement gap; 
 selecting one or more items of supplemental content, each item of supplemental content characterized by one or more deficient topics; and 
 sending the selected items of supplemental content to the browser. 
   
     
     
         2 . The method of  claim 1 , wherein measuring the browser's off-site engagement with each of the plurality of topics according to visits by the browser to the plurality of off-site web pages is further according to a type of interaction by the browser during visits to each of the plurality of off-site web pages. 
     
     
         3 . The method of  claim 1 , wherein measuring the browser's off-site engagement with each of the plurality of topics according to visits by the browser to the plurality of off-site web pages is further according to a frequency of visitation by the browser to each the plurality of off-site web pages. 
     
     
         4 . The method of  claim 1 , wherein each of the on-site topic strengths corresponding to each of the on-site topics of each of the plurality of web pages of the target website is based on how frequently at least one of words, sounds, and images associated with the topic occur on the web page of the target website. 
     
     
         5 . The method of  claim 1 , wherein each of the on-site topic strengths corresponding to each of the on-site topics of each of the plurality of web pages of the target website is based on the size of one of at least one words, sounds, and images associated with the topic on the web page of the target website. 
     
     
         6 . The method of  claim 1 , wherein each of the on-site topic strengths corresponding to each of the on-site topics of each of the plurality of web pages of the target website is based on the position of one at least one of words, sounds, and images associated with the topic on the web page of the target website. 
     
     
         7 . The method of  claim 1 , wherein each of the on-site topic strengths corresponding to each of the on-site topics of each of the plurality of web pages of the target website is based on the confidence that the identification of each of the on-site topic strengths corresponding to each of the on-site topics of each of the plurality of web pages of the target website is accurate. 
     
     
         8 . The method of  claim 7 , wherein the confidence that the identification of each of the on-site topic strengths corresponding to each of the on-site topics of each of the plurality of web pages of the target website is accurate is determined using natural language processing of each of the plurality of web pages of the target website. 
     
     
         9 . A non-transitory computer-readable storage medium storing processor-executable computer program instructions that, when executed, cause a computer processor to perform a method, the method comprising:
 receiving notification of a browser's request of a web page of a target website, the target website comprising a plurality of web pages, each web page having an on-site topic and each on-site topic having an on-site topic strength; and   responsive to receiving the notification, sending supplemental content to the browser before the web page finishes loading by:
 measuring the browser's on-site engagement with each of a plurality of topics according to visits by the browser to a plurality of web pages of the target website and according to the on-site topic strength of the corresponding on-site topic of each of the plurality of web pages of the target website, wherein the plurality of web pages of the target website operate in a first domain controlled by a first business entity; 
 measuring the browser's off-site engagement with each of the plurality of topics according to visits by the browser to a plurality of off-site web pages, wherein the plurality of off-site web-pages operate in a second domain controlled by a second business entity, each of the plurality of off-site web pages having an off-site topic corresponding to one of the plurality of topics; and 
 determining an engagement gap corresponding to each of the plurality of topics by subtracting the corresponding measured on-site engagement from the corresponding measured off-site engagement; 
 identifying deficient topics, wherein a deficient topic has a positive engagement gap; 
 selecting one or more items of supplemental content, each item of supplemental content characterized by one or more deficient topics; and 
 sending the selected items of supplemental content to the browser. 
   
     
     
         10 . The medium of  claim 9 , wherein measuring the browser's off-site engagement with each of the plurality of topics according to visits by the browser to the plurality of off-site web pages is further according to a type of interaction by the browser during visits to each of the plurality of off-site web pages. 
     
     
         11 . The medium of  claim 9 , wherein measuring the browser's off-site engagement with each of the plurality of topics according to visits by the browser to the plurality of off-site web pages is further according to a frequency of visitation by the browser to each the plurality of off-site web pages. 
     
     
         12 . The medium of  claim 9 , wherein each of the on-site topic strengths corresponding to each of the on-site topics of each of the plurality of web pages of the target website is based on how frequently at least one of words, sounds, and images associated with the topic occur on the web page of the target website. 
     
     
         13 . The medium of  claim 9 , wherein each of the on-site topic strengths corresponding to each of the on-site topics of each of the plurality of web pages of the target website is based on the size of one of at least one words, sounds, and images associated with the topic on the web page of the target website. 
     
     
         14 . The medium of  claim 9 , wherein each of the on-site topic strengths corresponding to each of the on-site topics of each of the plurality of web pages of the target website is based on the position of one at least one of words, sounds, and images associated with the topic on the web page of the target website. 
     
     
         15 . The medium of  claim 9 , wherein each of the on-site topic strengths corresponding to each of the on-site topics of each of the plurality of web pages of the target website is based on the confidence that the identification of each of the on-site topic strengths corresponding to each of the on-site topics of each of the plurality of web pages of the target website is accurate. 
     
     
         16 . The medium of  claim 15 , wherein the confidence that the identification of each of the on-site topic strengths corresponding to each of the on-site topics of each of the plurality of web pages of the target website is accurate is determined using natural language processing of each of the plurality of web pages of the target website. 
     
     
         17 . A system comprising:
 a processor; and   a non-transitory computer-readable storage medium storing processor-executable computer program instructions that, when executed, cause a computer processor to perform a method, the method comprising:
 receiving notification of a browser's request of a web page of a target website, the target website comprising a plurality of web pages, each web page having an on-site topic and each on-site topic having an on-site topic strength; and 
 responsive to receiving the notification, sending supplemental content to the browser before the web page finishes loading by:
 measuring the browser's on-site engagement with each of a plurality of topics according to visits by the browser to a plurality of web pages of the target website and according to the on-site topic strength of the corresponding on-site topic of each of the plurality of web pages of the target website, wherein the plurality of web pages of the target website operate in a first domain controlled by a first business entity; 
 measuring the browser's off-site engagement with each of the plurality of topics according to visits by the browser to a plurality of off-site web pages, wherein the plurality of off-site web-pages operate in a second domain controlled by a second business entity, each of the plurality of off-site web pages having an off-site topic corresponding to one of the plurality of topics; and 
 determining an engagement gap corresponding to each of the plurality of topics by subtracting the corresponding measured on-site engagement from the corresponding measured off-site engagement; 
 identifying deficient topics, wherein a deficient topic has a positive engagement gap; 
 selecting one or more items of supplemental content, each item of supplemental content characterized by one or more deficient topics; and 
 sending the selected items of supplemental content to the browser. 
 
   
     
     
         18 . The system of  claim 17 , wherein measuring the browser's off-site engagement with each of the plurality of topics according to visits by the browser to the plurality of off-site web pages is further according to a type of interaction by the browser during visits to each of the plurality of off-site web pages. 
     
     
         19 . The system of  claim 17 , wherein measuring the browser's off-site engagement with each of the plurality of topics according to visits by the browser to the plurality of off-site web pages is further according to a frequency of visitation by the browser to each the plurality of off-site web pages. 
     
     
         20 . The system of  claim 17 , wherein each of the on-site topic strengths corresponding to each of the on-site topics of each of the plurality of web pages of the target website is based on how frequently at least one of words, sounds, and images associated with the topic occur on the web page of the target website. 
     
     
         21 . The system of  claim 17 , wherein each of the on-site topic strengths corresponding to each of the on-site topics of each of the plurality of web pages of the target website is based on the size of one of at least one words, sounds, and images associated with the topic on the web page of the target website. 
     
     
         22 . The system of  claim 17 , wherein each of the on-site topic strengths corresponding to each of the on-site topics of each of the plurality of web pages of the target website is based on the position of one at least one of words, sounds, and images associated with the topic on the web page of the target website. 
     
     
         23 . The system of  claim 17 , wherein each of the on-site topic strengths corresponding to each of the on-site topics of each of the plurality of web pages of the target website is based on the confidence that the identification of each of the on-site topic strengths corresponding to each of the on-site topics of each of the plurality of web pages of the target website is accurate. 
     
     
         24 . The system of  claim 23 , wherein the confidence that the identification of each of the on-site topic strengths corresponding to each of the on-site topics of each of the plurality of web pages of the target website is accurate is determined using natural language processing of each of the plurality of web pages of the target website.