System and method for spam identification

Abstract

A system and method are provided for improving a user search experience by identifying spam results in a result set produced in response to a query. The system may include a user interface spam feedback mechanism for allowing a user to indicate that a given result is spam. The system may additionally include an automated spam identification mechanism for implementing automated techniques on the given result to determine whether the given result is spam. The system may further include a merging component for merging the determinations of the user interface spam feedback mechanism and the automated spam identification mechanism for deriving an indicator of the likelihood that a given result is spam.

1 . A method for improving a user search experience by identifying spam results in a result set produced in response to a query, the method comprising:
 receiving, at a computing device, a search query;   determining a monetization value for the search query;   returning a plurality of results that are responsive to the search query, wherein the plurality includes an individual result that is responsive to the search query;   calculating a probability that the individual result is spam using one or more automated spam identification techniques, wherein at least one of the one or more automated spam identification techniques uses the monetization value of the query to calculate the probability, wherein the probability that the individual result is spam is lower when the monetization value of the search query is lower; and   displaying the individual result and other results from the plurality in an order that is based on the probability that the individual result is spam.   
   
   
       2 . The method of  claim 1 , wherein the monetization value is calculated using information from an online advertising exchange. 
   
   
       3 . The method of  claim 1 , wherein the monetization value is based on bid rates for one or more terms in the search query, wherein higher bid rates indicate a higher monetization value for the search query. 
   
   
       4 . The method of  claim 1 , wherein the monetization value is based on clickthrough rates on sponsored sites for one or more terms in the search query, wherein higher clickthrough rates indicate a higher monetization value for the search query. 
   
   
       5 . The method of  claim 1 , receiving user feedback identifying the individual result as spam, wherein the user feedback is received through an input displayed when the individual result is presented within a plurality of search results in response to one or more queries. 
   
   
       6 . The method of  claim 5 , further comprising analyzing the user feedback for the individual result across multiple queries, wherein a confidence that the individual result is spam is increased when the user feedback is received in connection with presenting the individual result in response to the multiple queries. 
   
   
       7 . The method of  claim 6 , merging data obtained from the user feedback and the one or more automated spam identification techniques to calculate the probability that the individual result is spam. 
   
   
       8 . The method of  claim 1 , wherein the one or more automated spam identification techniques comprise a popularity analysis that determines a popularity of the individual result by examining traffic to a website referenced by the individual result, wherein a high popularity indicates a lower probability that the individual result is spam. 
   
   
       9 . The method of  claim 8 , wherein the popularity analysis is based on traffic data obtained from search toolbars utilized by a plurality of users, wherein when the data indicates that many users visit the individual result, then the probability that the individual result is spam is decreased. 
   
   
       10 . One or more computer-readable media including computer-executable instructions, that when executed by a computing device, performs a method for improving a user search experience by identifying spam results in a result set produced in response to a query, the method comprising:
 receiving, at the computing device, a search query;   determining a monetization value for the search query;   returning a plurality of search results that are responsive to the search query, wherein the plurality includes an individual result that is responsive to the search query, and wherein the individual result is a website;   calculating a probability that the individual result is spam using one or more automated spam identification techniques, wherein at least one of the one or more automated spam identification techniques uses the monetization value of the query to calculate the probability, wherein the probability that the individual result is spam is lower when the monetization value of the search query is lower; and   displaying the individual result and other results from the plurality in an order that is based on the probability that the individual result is spam.   
   
   
       11 . The media of  claim 10 , wherein the monetization value is calculated using information from an online advertising exchange. 
   
   
       12 . The media of  claim 10 , wherein the monetization value is based on bid rates for one or more terms in the search query, wherein higher bid rates indicate a higher monetization value for the search query. 
   
   
       13 . The media of  claim 10 , wherein the monetization value is based on clickthrough rates on sponsored sites for one or more terms in the search query, wherein higher clickthrough rates indicate a higher monetization value for the search query. 
   
   
       14 . The media of  claim 10 , wherein the one or more automated spam identification techniques comprise a popularity analysis that determines a popularity of the individual result by examining traffic to the individual result, wherein a high popularity indicates a lower probability that the individual result is spam. 
   
   
       15 . The media of  claim 14 , wherein the popularity analysis is based on traffic data obtained from search toolbars utilized by a plurality of users, wherein when the data indicates that many users visit the individual result, then the probability that the individual result is spam is decreased. 
   
   
       16 . The media of  claim 10 , wherein the one or more automated spam identification techniques comprise analyzing how many advertisements are included on the individual result. 
   
   
       17 . One or more computer-readable media including computer-executable instructions, that when executed by a computing device, performs a method for improving a user search experience by identifying spam results in a result set produced in response to a query, the method comprising:
 receiving, at the computing device, a search query;   determining a monetization value for the search query;   returning a plurality of results that are responsive to the search query, wherein the plurality includes an individual result that is responsive to the search query;   ranking the individual result relative to other results in the plurality based on responsiveness to the search query;   calculating a probability that the individual result is spam using one or more automated spam identification techniques;   adjusting a rank of the individual result based on the probability and the monetization value of the search query, wherein less adjustment to the rank is made when the monetization value of the search query is low;   displaying the individual result and other results in an order that is based on the probability that the individual result is spam.   
   
   
       18 . The media of  claim 17 , wherein the monetization value is calculated using information from an online advertising exchange. 
   
   
       19 . The media of  claim 17 , wherein the monetization value is based on bid rates for one or more terms in the search query, wherein higher bid rates indicate a higher monetization value for the search query. 
   
   
       20 . The media of  claim 17 , wherein the monetization value is based on clickthrough rates on sponsored sites for one or more terms in the search query, wherein higher clickthrough rates indicate a higher monetization value for the search query.