Method of and system for determining user-specific proportions of content for recommendation

A computer-implemented method for determining user-specific proportions of at least two types of content for content recommendations to a given user, the given user being associated with an electronic device, the electronic device being connected to a server over a communication network, the server hosting a content recommendation service, the content recommendation service for generating the content recommendations having content items of the at least two types of content,

• the method executable by the server, the method comprising:
• acquiring, by the server, for each respective type of content of the at least two types of content, an indication of a respective base interval of proportion;
• acquiring, by the server, for each respective type of content of the at least two types of content, a respective set of user interaction parameters, the respective set of user interaction parameters being indicative of user engagement of a respective set of users of the content recommendation service with the respective type of content;
• computing, by the server, for each respective type of content of the at least two types of content, an associated respective distribution of user interaction parameters based on the respective set of user interaction parameters of the respective set of users;
• in response to receiving an indication of a personalized content request from the electronic device associated with the given user:
• acquiring, by the server, for each respective type of content of the at least two types of content, an associated respective user-specific interaction parameter of the given user, the associated respective user-specific interaction parameter being indicative of user preference of the given user for the respective type of content;
• computing, by the server, for each respective type of content of the at least two types of content, a respective user-specific proportion of the respective type of content for content recommendation to the given user, the respective user-specific proportion being within the respective base interval of proportion, the computing being based on:
• the associated respective distribution of user interaction parameters of the set of users, and
• the associated respective user-specific interaction parameter of the given user;
• generating, by the content recommendation service of the server, a plurality of content items for personalized content recommendation for the given user, the plurality of content items being of the at least two types of content, a respective portion of the plurality of content items being within the respective user-specific proportion;
• and
• sending, by the server, the plurality of content items for displaying on the electronic device of the given user.