Schema augmentation system for exploratory research

A method for schematizing content based on user interactions by user, comprising:

• generating a user interface comprising a display of first content;
• receiving user behavior input via the user interface;
• processing the user behavior input according to a machine learning model configured to derive semantics according to the machine learning model;
• computing a schema intent by analyzing a proximity of semantics associated with the first content;
• generating a schematization map associating a first information unit of the first content with a second information unit determined to be proximate to the first information unit;
• displaying, via the user interface, an indication of the second information unit as a proposed information unit associated with the schema intent;
• obtaining a user evaluation input corresponding to the proposed information unit;
• and
• training the schematization map based on the user evaluation input,
• wherein the schema intent is formed based at least in part on a semantic proximity of the first information unit and a second content as determined based at least in part on user input.

A computer system for schematizing content obtained by user, comprising:

• at least one processor;
• and
• memory storing instructions that, when executed by the at least one processor, causes the at least one processor to perform a set of operations, the set of operations comprising:
• displaying a user interface comprising content from a content source;
• receiving, via the user interface, user input comprising:
• a user interaction with the content source;
• a user selection of a first information unit from the content;
• or
• an indication of a user grouping of a first information unit from the content;
• processing the user input according to a machine learning model configured to derive semantics according to the machine learning model;
• determining a schema intent by analyzing a proximity of semantics associated with the first information unit;
• determining, based at least in part on the schema intent, a schematization map associating a second information unit determined to be semantically proximate to the first information unit;
• displaying, via the user interface, an indication of the second information unit as a proposed information unit associated with the schema intent;
• obtaining a user evaluation input corresponding to the schema intent;
• and
• training and updating the schematization map based on the user evaluation input.