Method and system for recommending content
The present teaching relates to recommending content by analyzing the streamed data. A request is received from a user requesting one or more recommendations from a set of items. A first distribution indicative of an interest distribution of the user in a plurality of topics is obtained. For each item, a second distribution indicative of a classification distribution of the item with respect to the plurality of topics is obtained. A score is estimated based on the first distribution and the second distribution, wherein the score indicates likelihood that the user is interested in the item. The scores associated with the set of items are ranked. The one or more recommendations are presented based on the ranked scores.
1. A method for content recommendation, comprising:
receiving, by a content recommendation computing system, a real-time data stream over a network;
retrieving, from a database, an average classification distribution of existing content items with respect to a plurality of topics;
in response to analyzing the real-time data stream to determine an event from the real-time data stream being a new user;
initializing, based on an average interest distribution of existing users on the plurality of topics, an interest distribution for the new user with respect to the plurality of topics, and
updating, based on activities of the new user, the interest distribution and the average interest distribution of existing users on the plurality of topics; and
in response to analyzing the real-time data stream to determine an event from the real-time data stream being a new content item;
initializing, based on the average classification distribution of existing content items, a classification distribution of the new content item with respect to the plurality of topics, and
updating, based on activities of users directed to the new content item, the classification distribution and the average classification distribution of existing content items with respect to the plurality of topics;
further updating the updated classification distribution based on a shift of the new content from a first topic of the plurality of topics to a second topic of the plurality of topics;
updating the database based on the further updated classification distribution;
estimating a set of correlation values based on the updated interest distribution and the further updated classification distribution;
adjusting the set of correlation values based on a shift of the new user's interest;
selecting at least one content item from the existing content items based on the adjusted set of correlation values; and
recommending the selected at least one content item to the user.
2. The method of claim 1 , wherein the activities of the new user comprise a rating from the new user.
3. The method of claim 1 , wherein the updated interest distribution comprises a first plurality of values each representing an interest of the new user in a respective one of the plurality of topics.
4. Method of claim 1 , wherein the further updated classification distribution comprises a second plurality of values each representing a frequency of the new content item being classified into a respective one of the plurality of topics.
5. The method of claim 1 , further comprising:
comparing the set of correlation values with historical data to determine the shift of the new user's interest from one of the plurality of topics to another one of the plurality of topics within a predetermined time period.
6. The method of claim 5 , wherein each of the set of correlation values indicates a rating from the new user to a corresponding existing content item.
7. The method of claim 1 , further comprising:
receiving a new rating of an existing content item from an existing user;
updating an interest distribution associated with the existing user based on the new rating; and
updating a classification distribution associated with the existing content item based on the new rating.
8. A non-transitory, computer-readable medium having information recorded thereon for content recommendation, wherein the information, when read by a machine, causes the machine to perform operations comprising:
receiving, by a content recommendation computing system, a real-time data stream over a network;
retrieving, from a database, an average classification distribution of existing content items with respect to a plurality of topics;
in response to analyzing the real-time data stream to determine an event from the real-time data stream being a new user;
initializing, based on an average interest distribution of existing users on the plurality of topics, an interest distribution for the new user with respect to the plurality of topics, and
updating, based on activities of the new user, the interest distribution and the average interest distribution of existing users on the plurality of topics; and
in response to analyzing the real-time data stream to determine an event from the real-time data stream being a new content item;
initializing, based on the average classification distribution of existing content items, a classification distribution of the new content item with respect to the plurality of topics, and
updating, based on activities of users directed to the new content item, the classification distribution and the average classification distribution of existing content items with respect to the plurality of topics;
further updating the updated classification distribution based on a shift of the new content from a first topic of the plurality of topics to a second topic of the plurality of topics;
updating the database based on the further updated classification distribution;
estimating a set of correlation values based on the updated interest distribution and the further updated classification distribution;
adjusting the set of correlation values based on a shift of the new user's interest;
selecting at least one content item from the existing content items based on the adjusted set of correlation values; and
recommending the selected at least one content item to the user.
9. The medium of claim 8 , wherein the activities of the new user comprise a rating from the new user.
10. The medium of claim 8 , wherein the updated interest distribution comprises a first plurality of values each representing an interest of the new user in a respective one of the plurality of topics.
11. The medium of claim 8 , wherein the further updated classification distribution comprises a second plurality of values each representing a frequency of the new content item being classified into a respective one of the plurality of topics.
12. The medium of claim 8 , wherein the operations further comprise:
comparing the set of correlation values with historical data to determine the shift of the new user's interest from one of the plurality of topics to another one of the plurality of topics within a predetermined time period.
13. The medium of claim 12 , wherein each of the set of correlation values indicates a rating from the new user to a corresponding existing content item.
14. The medium of claim 8 , wherein the operations further comprise:
receiving a new rating of an existing content item from an existing user;
updating an interest distribution associated with the existing user based on the new rating; and
updating a classification distribution associated with the existing content item based on the new rating.
15. A system for content recommendation, the system comprising:
memory storing computer program instructions; and
one or more processors that, in response to executing the computer program instructions, effectuate operations comprising:
receiving, by a content recommendation computing system, a real-time data stream over a network;
retrieving, from a database, an average classification distribution of existing content items with respect to a plurality of topics;
in response to analyzing the real-time data stream to determine an event from the real-time data stream being a new user;
initializing, based on an average interest distribution of existing users on the plurality of topics, an interest distribution for the new user with respect to the plurality of topics, and
updating, based on activities of the new user, the interest distribution and the average interest distribution of existing users on the plurality of topics; and
in response to analyzing the real-time data stream to determine an event from the real-time data stream being a new content item;
initializing, based on the average classification distribution of existing content items, a classification distribution of the new content item with respect to the plurality of topics, and
updating, based on activities of users directed to the new content item, the classification distribution and the average classification distribution of existing content items with respect to the plurality of topics;
further updating the updated classification distribution based on a shift of the new content from a first topic of the plurality of topics to a second topic of the plurality of topics;
updating the database based on the further updated classification distribution;
estimating a set of correlation values based on the updated interest distribution and the further updated classification distribution;
adjusting the set of correlation values based on a shift of the new user's interest;
selecting at least one content item from the existing content items based on the adjusted set of correlation values; and
recommending the selected at least one content item to the user.
16. The system of claim 15 , wherein the activities of the new user comprise a rating from the new user.
17. The system of claim 15 , wherein the updated interest distribution comprises a first plurality of values each representing an interest of the new user in a respective one of the plurality of topics.
18. The system of claim 15 , wherein the further updated classification distribution comprises a second plurality of values each representing a frequency of the new content item being classified into a respective one of the plurality of topics.
19. The system of claim 15 , wherein the operations further comprise:
comparing the set of correlation values with historical data to determine the shift of the new user's interest from one of the plurality of topics to another one of the plurality of topics within a predetermined time period.
20. The system of claim 19 , wherein each of the set of correlation values indicates a rating from the new user to a corresponding existing content item.