Real Time Query Trends with Multi-Document Summarization

Abstract

A list of “hot topics” may be provided to a user to indicate information that is currently popular. A topic may be deemed popular when a large number of search queries related to the topic are entered by users. A search system may receive and analyze an electronic source of published information to determine a reason for why a particular popular topic is popular. If content related to why a particular popular topic is popular exists in multiple electronic sources of published information, text summarization techniques may be used to determine a reason for why the popular topic is popular by from among the multiple electronic sources of published information.

What is claimed is: 
     
         1 . A method for presenting a reason that a search topic is popular, the method comprising:
 receiving an indication of a search topic that is popular;   in response to receiving the indication of the search topic that is popular, identifying, from among multiple articles, a subset of the multiple articles that were published less than a threshold period of time prior to the search topic becoming popular and include content that matches the search topic that is popular;   determining, using at least one processor, a summary of content from the identified subset of the multiple articles that were published less than the threshold period of time prior to the search topic becoming popular and include content that matches the search topic that is popular; and   presenting, to at least one user, the determined summary as a reason that the search topic is popular.   
     
     
         2 . The method of  claim 1  further comprising creating a list of identified trend-determined reason pairs by repeating the receiving, identifying, and determining for multiple search topics. 
     
     
         3 . The method of  claim 1  further comprising accessing search popularity information stored in a computer storage medium that includes search topics and reasons, wherein:
 a search topic is associated with at least one reason for popularity of the search topic, and 
 the at least one reason for popularity of the search topic is determined by analyzing at least one content feed from an electronic source of published information. 
 
     
     
         4 . The method of  claim 3  wherein the search popularity information also includes a category associated with a search topic, the method further comprising:
 receiving an indication of a category; 
 accessing the search popularity information to determine a search topic associated with the indicated category; and 
 presenting the search topic associated with the indicated category and the at least one reason for popularity of the search topic. 
 
     
     
         5 . The method of  claim 1  further comprising analyzing multiple search queries to identify a search topic that is popular. 
     
     
         6 . The method of  claim 5  wherein analyzing multiple search queries to identify a search topic that is popular comprises:
 determining a number of search queries received during a first predetermined period of time, the search queries identifying a particular entity; 
 determining a number of search queries received during a second predetermined period of time, the search queries identifying the particular entity; 
 comparing the number of search queries received during the first and second predetermined periods of time; and 
 based on the comparison, determining whether a search topic related to the particular entity is popular. 
 
     
     
         7 . The method of  claim 1  wherein the multiple articles include articles from at least one of electronic data feeds, news, weblogs, or other online content. 
     
     
         8 . The method of  claim 7  wherein the electronic data feeds include RSS. 
     
     
         9 . The method of  claim 1  wherein the multiple articles include data in the form of at least one of audio, video, text, audible text after a text-to-speech conversion, images and animation. 
     
     
         10 . The method of  claim 1  wherein identifying, from among multiple articles, the subset of the multiple articles that were published less than a threshold period of time prior to the search topic becoming popular comprises identifying articles from an electronic source of published information that includes content published less than a threshold number of days prior to the search topic becoming popular. 
     
     
         11 . The method of  claim 1  wherein presenting, to at least one user, the determined summary as a reason that the search topic is popular comprises presenting, with the search topic that is popular and the determined reason that the search topic is popular, an indication of a time when the reason was determined. 
     
     
         12 . The method of  claim 1  wherein identifying, from among multiple articles, the subset of the multiple articles that were published less than a threshold period of time prior to the search topic becoming popular and include content that matches the search topic that is popular comprises excluding articles published more than a threshold period of time prior to the search topic becoming popular and excluding articles that are not relevant to the search topic. 
     
     
         13 . The method of  claim 1  wherein identifying, from among multiple articles, the subset of the multiple articles that were published less than a threshold period of time prior to the search topic becoming popular and include content that matches the search topic that is popular comprises:
 receiving multiple content feeds, and 
 selecting a subset of the multiple content feeds that each include an article that was published less than a threshold period of time prior to the search topic becoming popular and that is relevant to the search topic, the selected subset of content feeds being less than all of the multiple content feeds. 
 
     
     
         14 . A system comprising:
 at least one computer; and   at least one computer-readable medium coupled to the at least one computer having instructions stored thereon which, when executed by the at least one computer, cause the at least one computer to perform operations comprising:
 receiving an indication of a search topic that is popular; 
 in response to receiving the indication of the search topic that is popular, identifying, from among multiple articles, a subset of the multiple articles that were published less than a threshold period of time prior to the search topic becoming popular and include content that matches the search topic that is popular; 
 determining, using at least one processor, a summary of content from the identified subset of the multiple articles that were published less than the threshold period of time prior to the search topic becoming popular and include content that matches the search topic that is popular; and 
   presenting, to at least one user, the determined summary as a reason that the search topic is popular.   
     
     
         15 . The system of  claim 14  wherein the multiple articles include articles from at least one of electronic data feeds, news, weblogs, or other online content. 
     
     
         16 . The system of  claim 14  wherein identifying, from among multiple articles, the subset of the multiple articles that were published less than a threshold period of time prior to the search topic becoming popular comprises identifying articles from an electronic source of published information that includes content published less than a threshold number of days prior to the search topic becoming popular. 
     
     
         17 . The system of  claim 14  wherein presenting, to at least one user, the determined summary as a reason that the search topic is popular comprises presenting, with the search topic that is popular and the determined reason that the search topic is popular, an indication of a time when the reason was determined. 
     
     
         18 . The system of  claim 14  wherein identifying, from among multiple articles, the subset of the multiple articles that were published less than a threshold period of time prior to the search topic becoming popular and include content that matches the search topic that is popular comprises excluding articles published more than a threshold period of time prior to the search topic becoming popular and excluding articles that are not relevant to the search topic. 
     
     
         19 . The system of  claim 14  wherein identifying, from among multiple articles, the subset of the multiple articles that were published less than a threshold period of time prior to the search topic becoming popular and include content that matches the search topic that is popular comprises: receiving multiple content feeds, and
 selecting a subset of the multiple content feeds that each include an article that was published less than a threshold period of time prior to the search topic becoming popular and that is relevant to the search topic, the selected subset of content feeds being less than all of the multiple content feeds. 
 
     
     
         20 . At least one computer-readable storage medium encoded with executable instructions that, when executed by at least one processor, cause the at least one processor to perform operations comprising:
 receiving an indication of a search topic that is popular;   in response to receiving the indication of the search topic that is popular, identifying, from among multiple articles, a subset of the multiple articles that were published less than a threshold period of time prior to the search topic becoming popular and include content that matches the search topic that is popular;   determining, using at least one processor, a summary of content from the identified subset of the multiple articles that were published less than the threshold period of time prior to the search topic becoming popular and include content that matches the search topic that is popular; and   presenting, to at least one user, the determined summary as a reason that the search topic is popular.