Determining information inter-relationships from distributed group discussions

Abstract

Techniques are described for analyzing user-supplied information and/or predicting future aspects of additional information that will be supplied by users. The analyzed information may include distributed group discussions involving numerous users, occurring via user comments and other content items supplied to social networking site(s) and/or other sources. Analysis of user-supplied information may, for example, include determining particular topics and/or categories of interest during one or more time periods and quantifying corresponding amounts of user interest; determining trends for, relevant terms and attributes for, and inter-relationships between the topics and categories; predicting future amounts of user interest in the topics and categories; tracking user interactions with information about the topics and/or categories; and taking further actions based on the analyzed and/or predicted information.

1 - 39 . (canceled) 
     
     
         40 . A system, comprising:
 one or more hardware processors of one or more computer systems; and   one or more memories including instructions that, when executed by at least one hardware processor of the one or more hardware processors, cause the at least one hardware processor to determine relevant information for a distributed group discussion involving a plurality of users submitting a plurality of textual comments for the distributed group discussion, the determining of the relevant information including:
 analyzing the plurality of textual comments to identify a plurality of topics, wherein each topic of the plurality is mentioned in contents of one or more of the plurality of textual comments; 
 generating a plurality of comment groups based on the identified topics, each of the generated comment groups being associated with one of the identified topics and including one or more of the plurality of textual comments that have contents mentioning the associated identified topic; 
 analyzing, for each of the plurality of comment groups, the one or more textual comments included in the comment group to determine one or more attributes for the comment group that are distinct from the associated topic for the comment group; 
 determining one or more inter-relationships that are each between two or more of the plurality of comment groups based at least in part on the determined one or more attributes for each of the two or more comment groups of the inter-relationship; and 
 providing information to at least one user about at least one of the determined one or more inter-relationships. 
   
     
     
         41 . The system of  claim 40  wherein at least some of the determined attributes for at least some of the plurality of comment groups are terms included in contents of the plurality of textual comments, and wherein the instructions further cause the at least one hardware processor to display information to at least one user about one or more determined attributes for one or more of the plurality of comment groups. 
     
     
         42 . The system of  claim 40  wherein the determining of the relevant information further includes:
 determining, for each of multiple content categories, multiple comment groups that are a subset of the plurality of generated comment groups and that correspond to one or more definition terms for the content category; 
 analyzing, for each of the multiple content categories, the textual comments included in the multiple comment groups corresponding to the content category to determine one or more attributes for the content category that are distinct from the definition terms for the content category; and 
 providing information to the at least one user about at least one of the determined attributes for at least one of the multiple content categories. 
 
     
     
         43 . The system of  claim 42  wherein at least some of the determined attributes for at least some of the multiple content categories are terms included in contents of the plurality of textual comments, and wherein the determining of the one or more inter-relationships includes determining that the at least one determined inter-relationship is between two or more comment groups associated with two or more of the multiple content categories. 
     
     
         44 . (canceled) 
     
     
         45 . The system of  claim 42  wherein the determining of the one or more inter-relationships further includes determining that the at least one determined inter-relationship is between two or more of the multiple content categories that include the two or more comment groups of the at least one determined inter-relationship. 
     
     
         46 . The system of  claim 40  wherein the one or more computer systems are part of a group discussion analysis and prediction service and the at least one user is an end-user of the group discussion analysis and prediction service, and wherein the providing of the information to the at least one user includes sending information over one or more computer networks from the group discussion analysis and prediction service to a client device of a user of the at least one user for display using an application from the group discussion analysis and prediction service that is executing on the client device. 
     
     
         47 . The system of  claim 40  wherein the one or more computer systems are part of a group discussion analysis and prediction service, wherein the instructions further cause the at least one hardware processor to provide, by the group discussion analysis and prediction service, additional information to one or more advertisers from the determining of the relevant information, the provided additional information including at least one of determined attributes for two or more of the comment groups or information about at least one determined inter-relationship between two or more of the plurality of comment groups, and wherein the providing of the information to the user includes providing promotional information from at least one advertiser in response to instructions from the at least one advertiser based on the provided additional information. 
     
     
         48 . A computer-implemented method, comprising:
 generating, by one or more computing systems, a plurality of comment groups for a plurality of topics, wherein each of the generated comment groups is associated with one of the topics and includes one or more comments having contents mentioning the associated topic for the comment group, and wherein the one or more comments for each of the plurality of comment groups are selected from a plurality of comments received from a plurality of users;   analyzing, by the one or more computing systems and for each of the plurality of comment groups, the one or more comments included in the comment group to determine one or more attributes for the comment group that are distinct from the associated topic for the comment group;   determining, by the one or more computing systems and based at least in part on the determined attributes for two or more comment groups, one or more inter-relationships including the two or more comment groups; and   providing, by the one or more computing systems, information to a user about the determined one or more inter-relationships.   
     
     
         49 . The computer-implemented method of  claim 48  further comprising analyzing, by the one or more computing systems and for multiple content categories that each include multiple comment groups of the plurality of comment groups, the comments included in the multiple comment groups for each of the content categories to determine one or more attributes for the content category,
 and wherein the determining of the one or more inter-relationships includes identifying the one or more inter-relationships as being between two or more of the content categories that include the two or more comment groups, 
 and wherein the providing of the information to the user includes identifying the two or more content categories. 
 
     
     
         50 . The computer-implemented method of  claim 48  wherein at least some of the determined attributes for the two or more comment groups are terms in contents of the comments included in the two or more comment groups, and wherein the providing of the information to the user includes displaying information to the user about one or more of the at least some determined attributes. 
     
     
         51 . The computer-implemented method of  claim 48  wherein the one or more computing systems are part of a group discussion analysis and prediction service and the user is an end-user of the group discussion analysis and prediction service, and wherein the providing of the information to the user includes sending information over one or more computer networks from the group discussion analysis and prediction service to a client device of the user for display using an application from the group discussion analysis and prediction service that is executing on the client device. 
     
     
         52 . The computer-implemented method of  claim 48  wherein the one or more computing systems are part of a group discussion analysis and prediction service, and wherein the providing of the information to the user further includes providing promotional information from at least one advertiser in response to instructions from the at least one advertiser corresponding to at least one of the determined attributes for the two or more comment groups. 
     
     
         53 . The computer-implemented method of  claim 48  further comprising:
 identifying, by the one or more computing systems, a subset of the plurality of comments that are associated with a specified content category based on contents of the comments of the identified subset, wherein the comments of the identified subset are included in multiple of the generated comment groups; 
 determining, by the one or more computing systems, a subset of the generated comment groups that correspond to the specified content category; 
 discovering, by the one or more computing systems, additional content categories that are related to the specified content category, wherein each of the additional content categories corresponds to the topic of at least one of the determined subset of generated comment groups; and 
 providing, by the one or more computing systems, indications of the discovered additional content categories that are related to the specified content category. 
 
     
     
         54 . The computer-implemented method of  claim 48  further comprising:
 determining, by the one or more computing systems, and for each of the two or more comment groups, a quantity of the comments included in the comment group; 
 predicting, by the one or more computing systems, and for each of the two or more comment groups, an expected quantity of future comments associated with the identified topic for the comment group that will be supplied by human users during a future time period, the predicting being based in part on the determined quantity for the comment group; and 
 providing, by the one or more computing systems, an indication of the predicted expected quantity of future comments for at least one of the two or more comment groups. 
 
     
     
         55 . The computer-implemented method of  claim 48  further comprising:
 determining, by the one or more computing systems, and for each of multiple comment groups included in a specified content category, a quantity of the comments included in the comment group; 
 predicting, by the one or more computing systems, an expected quantity of future comments associated with the specified content category that will be supplied by human users during a future time period, the predicting being based in part on the determined quantities for the multiple comment groups; and 
 providing, by the one or more computing systems, an indication of the predicted expected quantity of future comments for the specified content category. 
 
     
     
         56 . The computer-implemented method of  claim 48  wherein the determining of the one or more attributes for the two or more comment groups includes determining one or more geographical locations from which comments included in the two or more comment groups are supplied, and wherein the determining of the one or more inter-relationships are based at least in part on the determined one or more geographical locations. 
     
     
         57 . The computer-implemented method of  claim 48  wherein the determining of the one or more attributes for the two or more comment groups includes determining one or more human users who supply comments included in the two or more comment groups, and wherein the determining of the one or more inter-relationships are based at least in part on the determined one or more human users. 
     
     
         58 . The computer-implemented method of  claim 48  wherein the plurality of comments are supplied to a plurality of information sources, wherein the determining of the one or more attributes for the two or more comment groups includes determining one or more of the information sources to which comments included in the two or more comment groups are supplied, and wherein the determining of the one or more inter-relationships are based at least in part on the determined one or more information sources. 
     
     
         59 . The computer-implemented method of  claim 48  further comprising:
 receiving, by the one or more computing systems, information about a succession of multiple comment groups that one or more users select; and 
 providing, by the one or more computing systems, information to initiate display of information to the user about the succession of the multiple comment groups. 
 
     
     
         60 . A non-transitory computer-readable medium having stored contents that cause one or more computing systems to perform automated operations, including at least:
 generating, by the one or more computing systems, a plurality of comment groups for a plurality of topics, wherein each of the generated comment groups is associated with one of the topics and includes one or more comments having contents mentioning the associated topic for the comment group, and wherein the one or more comments for each of the plurality of comment groups are selected from a plurality of comments received from a plurality of users;   associating, by the one or more computing systems and for each of multiple content categories, multiple comment groups of the plurality of comment groups with the content category based at least in part on contents of the comments included in the multiple comment groups;   analyzing, by the one or more computing systems and for each of the multiple content categories, the one or more comments included in each of the multiple comment groups for the content category to determine one or more attributes for the content category;   determining, by the one or more computing systems and based at least in part on the determined attributes for two or more content categories, one or more inter-relationships including the two or more content categories; and   providing, by the one or more computing systems, information to a user about the determined one or more inter-relationships.   
     
     
         61 . The non-transitory computer-readable medium of  claim 60  wherein at least some of the determined attributes for the two or more content categories are terms in contents of comments included in comment groups of the two or more content categories, and wherein the providing of the information to the user includes displaying information to the user about one or more of the at least some determined attributes. 
     
     
         62 . The non-transitory computer-readable medium of  claim 60  wherein the one or more computing systems are part of a group discussion analysis and prediction service and the user is an end-user of the group discussion analysis and prediction service, and wherein the providing of the information to the user includes sending information over one or more computer networks from the group discussion analysis and prediction service to a client device of the user for display using an application from the group discussion analysis and prediction service that is executing on the client device. 
     
     
         63 . The non-transitory computer-readable medium of  claim 60  wherein the one or more computing systems are part of a group discussion analysis and prediction service, and wherein the providing of the information to the user further includes providing promotional information from at least one advertiser in response to instructions from the at least one advertiser corresponding to at least one of the determined attributes for the two or more content categories. 
     
     
         64 . The non-transitory computer-readable medium of  claim 60  wherein the stored contents include software instructions that, when executed, further cause the one or more computing systems to:
 discover, by the one or more computing systems, additional content categories that are related to one of the content categories, wherein each of the additional content categories corresponds to the topic of at least one comment group included in the one content category; and 
 provide, by the one or more computing systems, indications of the discovered additional content categories that are related to the one content category. 
 
     
     
         65 . The non-transitory computer-readable medium of  claim 60  wherein the performing of the automated operations further includes:
 receiving, by the one or more computing systems, information about a succession of a plurality of content categories that one or more users select; and 
 providing, by the one or more computing systems, information to initiate display of information to the user about the succession of the plurality of content categories.