Social Network Based Recommendation Method and System

Abstract

Recommendations for content may be generated based on social networking communities. For example, a user may receive a list of recommended content items based on content that has been viewed by others in the user's social networks. Recommendations may further be based on content information such as reviews, ratings, tags, attributes and the like from various sources internal and external to the user's social networks. Content items may be given a weight that corresponds to a determined level of relevance or interest to a user. Using the weight, a list of recommended items may be sorted or filtered. In one or more configurations, the weight may be modified based on an age of the content item. For example, the relevance, importance or interest of a news report may decline as the news becomes older and older.

We claim: 
     
         1 . A computer-implemented method for making content recommendations comprising:
 identifying, by a computing device, a social network of which a first user is a member;   determining, by the computing device, a first content item accessed by a second user, the second user also being a member of the social network;   determining, by the computing device, a social network interest weight for the first content item by:
 determining a user weight of the second user, the user weight representing an importance of at least one of: the second user and a relationship with the second user within the social network; and 
 determining a normalized user weight for the second user by normalizing the user weight across multiple different social networks; and 
   ordering, by the computing device, a content recommendation list including the determined first content item based on the social network interest weight.   
     
     
         2 . A computer-implemented method for making content recommendations comprising:
 determining, by a computing device, multiple content items to recommend to a user;   ranking, by the computing device, the multiple content items based on a respective ranking value of each of the multiple content items, wherein the respective ranking value for each of the multiple content items is determined by:
 determining a decay rate corresponding to at least one of: a genre of the content item, the user, and a source of the content item; and 
 applying the decay rate to the ranking value; and 
   generating a list of the multiple content items according to the ranking values of the multiple content items.   
     
     
         3 . A computer-implemented method for making content recommendations comprising:
 generating a ranked list of recommended content items for a user;   generating a display including the ranked list of recommended content items, wherein the display includes:
 genre information for each of the recommended content items in the ranked list; and 
 a view option configured to request one of the recommended content items. 
   
     
     
         4 . The computer-implemented method of  claim 3 , wherein generating the display includes providing a recency control option in the display, the recency control option configured to modify a recency value for one or more of the content items, wherein the ranked list of recommended content items is at least partially ranked based on the recency value. 
     
     
         5 . The computer-implemented method of  claim 4 , wherein generating the display further includes adding an indicator for a first recommended content item, the indicator specifying that a ranking weight of the first recommended content item has been modified by a corresponding recency value.