System and method for evaluating and optimizing media content

Abstract

Systems and methods are described for evaluating and optimizing media content. A computer system for evaluating media content includes an input interface configured to receive a media content for evaluation by users in an online community, a media content presenter configured to present the media content to the users in the online community for evaluation, an informative signal monitor configured to gather informative signals relating to the media content from the users in the online community, a media content analyzer configured to evaluate the media content based on the informative signals from the users and generate an analysis result relating to the media content, and an incentive calculator configured to determine an incentive to one of the users in the online community based on the informative signals from the one of the users.

What is claimed is: 
     
         1 . A system comprising:
 one or more processors; and   memory storing instructions that, when executed by the one or more processors, cause the system to:
 provide, via a user interface, media content; 
 display, via the user interface, a user engagement panel; 
 receive, via the user engagement panel, user input relating to the media content; 
 evaluate the user input relating to the media content; 
 determine, based on evaluating the user input relating to the media content, an analysis result associated with an affinity level for an element of the media content; 
 construct a predictive computer model based on the media content and the analysis result associated with the affinity level for the element of the media content; 
 estimate, based on the predictive computer model, a different affinity level for a different element of different media content; and 
 provide, based on estimating the different affinity level for the different element of the different media content, a recommendation for the different element of the different media content. 
   
     
     
         2 . The system of  claim 1 , wherein the instructions, when executed by the one or more processors, further cause the system to:
 correlate a timestamp of the media content with the user input relating to the media content.   
     
     
         3 . The system of  claim 1 , wherein the instructions, when executed by the one or more processors, further cause the system to:
 determine a number of views of a portion of the media content, the portion comprising the element of the media content.   
     
     
         4 . The system of  claim 3 , wherein the instructions, when executed by the one or more processors, further cause the system to:
 determine a frequency of the number of views of the portion of the media content.   
     
     
         5 . The system of  claim 1 , wherein the instructions, when executed by the one or more processors, cause the system to:
 determine a number of shares of a portion of the media content, the portion comprising the element of the media content.   
     
     
         6 . The system of  claim 1 , wherein the instructions, when executed by the one or more processors, cause the system to:
 receive, as at least part of the user input relating to the media content, a tag relating to the media content; and   determine a timestamp of the element of the media content based on the tag relating to the media content.   
     
     
         7 . The system of  claim 1 , wherein the instructions, when executed by the one or more processors, cause the system to:
 receive, as at least part of the user input relating to the media content, at least one of a skip, a forward, a pause, or a rewind.   
     
     
         8 . The system of  claim 1 , wherein the instructions, when executed by the one or more processors, cause the system to:
 receive information regarding user interaction related to the element of the media content; and   based on the information regarding the user interaction related to the element of the media content, estimate the different affinity level for the different element of the different media content.   
     
     
         9 . The system of  claim 1 , wherein the instructions, when executed by the one or more processors, cause the system to:
 receive, as at least part of the user input relating to the media content, wherein the informative signals relating to the media content include engagement actions through the user engagement panel displayed on the user interface.   
     
     
         10 . The system of  claim 1 , wherein the instructions, when executed by the one or more processors, cause the system to:
 receive, as at least part of the user input relating to the media content, an engagement action including at least one of a sharing decision, a comment, a vote, or a selection of an emoticon.   
     
     
         11 . The system of  claim 10 , wherein the instructions, when executed by the one or more processors, cause the system to:
 determine a diffusion of the media content or of the element of the media content over a social media platform associated with the sharing decision.   
     
     
         12 . The system of  claim 10 , wherein the instructions, when executed by the one or more processors, cause the system to:
 determine, based on the engagement action, a degree of positivity toward the element of the media content.   
     
     
         13 . The system of  claim 1 , wherein the instructions, when executed by the one or more processors, cause the system to:
 perform sentiment analysis on one or more user comments associated with the media content; and   update, based on the sentiment analysis, the predictive computer model.   
     
     
         14 . The system of  claim 1 , wherein the instructions, when executed by the one or more processors, cause the system to:
 include, as part of the predictive computer model, at least one of a decision tree, a support vector machine, a graphical model, a non-parametric method, a neural network, a linear regression, or a hierarchical probabilistic model.   
     
     
         15 . The system of  claim 1 , wherein the instructions, when executed by the one or more processors, cause the system to:
 combine, before determining the recommendation for the different element of the different media content, user profile information with the analysis result associated with the affinity level for the element of the media content.   
     
     
         16 . A method comprising:
 providing, via a user interface of a system comprising memory and one or more processors, media content;   displaying, via the user interface of the system, a user engagement panel;   receiving, by the system and via the user engagement panel, user input relating to the media content;   evaluating, by the system, the user input relating to the media content;   determining, by the system and based on evaluating the user input relating to the media content, an analysis result associated with an affinity level for an element of the media content;   constructing, by the system, a predictive computer model based on the media content and the analysis result associated with the affinity level for the element of the media content;   estimating, by the system and based on the predictive computer model, a different affinity level for a different element of different media content; and   providing, by the system and based on estimating the different affinity level for the different element of the different media content, a recommendation for the different element of the different media content.   
     
     
         17 . The method of  claim 16 , comprising:
 providing the media content in a test format;   determining a user response to the test format; and   based on the user response to the test format, determining a prediction associated with the test format.   
     
     
         18 . The method of  claim 16 , comprising:
 recommending the different media content in a different format from a format of the media content.   
     
     
         19 . One or more non-transitory computer-readable media storing executable instructions that, when executed by one or more processors, cause a system to:
 provide, via a user interface, media content;   display, via the user interface, a user engagement panel;   receive, via the user engagement panel, user input relating to the media content;   evaluate the user input relating to the media content;   determine, based on evaluating the user input relating to the media content, an analysis result associated with an affinity level for an element of the media content;   construct a predictive computer model based on the media content and the analysis result associated with the affinity level for the element of the media content;   estimate, based on the predictive computer model, a different affinity level for a different element of different media content; and   provide, based on estimating the different affinity level for the different element of the different media content, a recommendation for the different element of the different media content.   
     
     
         20 . The one or more non-transitory computer-readable media of  claim 19 , wherein the executable instructions, when executed by the one or more processors, cause the system to:
 assign weight to the user input relating to the media content; and   evaluate the weighted user input relating to the media content as part of determining, based on evaluating the user input relating to the media content, the analysis result associated with the affinity level for the element of the media content.