Method and system for recommending content

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.

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.