Building a topical learning model in a content management system

A non-transitory computer readable storage medium storing computer program instructions for recommending a topic to a user of a content management system, the computer program instructions when executed by a processor causing the processor to:

• receive a plurality of topics extracted from documents of the content management system;
• generate pairings between the received topics, a pairing between two topics generated responsive to the two topics appearing in proximity to one another in one or more of the documents;
• determine a numerical complexity of each received topic, the numerical complexity comprising at least one of a vector representing a mean academic complexity of the topic and a vector representing a mean document complexity of the topic;
• generate a progression of the topics based on the numerical complexities of the topics and the pairings between the topics, the progression comprising a sequential ordering of paired topics in which each topic in the ordering has a higher numerical complexity than a preceding topic in the ordering;
• and
• responsive to a user of the content management system accessing content associated with a topic in the progression, recommend a next topic in the progression to the user.

A method for recommending a topic to a user of a content management system, the method comprising:

• extracting a plurality of topics from documents stored by the content management system;
• identifying topics, from the plurality of extracted topics, that appear in proximity to one another in the documents stored by the content management system from which the topics were extracted;
• for the topics identified as appearing in proximity to one another, determining a degree of correlation between the topics;
• generating pairings between the topics identified as appearing in proximity to one another based on the degree of correlation between the topics;
• determining a numerical complexity of each extracted topic, the numerical complexity comprising at least one of a vector representing a mean document complexity of the topic that is based on a complexity for each document from which each topic was extracted, and a vector representing a mean an academic complexity of the topic that is based on normalized locations of each topic within each document from which each topic was extracted;
• generating a progression of the topics based on the numerical complexities complexity of the topics and the pairings between the topics, the progression comprising a sequential ordering of paired topics in which each topic in the ordering has a higher complexity than a preceding topic;
• and
• responsive to a user of the content management system accessing content associated with a topic in the progression, recommending a next topic in the progression to the user.