Textbook content reorganization based on classroom analytics

A system comprising:

• one or more processors for executing computer-readable instructions, the computer-readable instructions controlling the one or more processors to perform operations comprising:
• receiving, by a processor, observation data about an activity;
• codifying the observation data to create codified observation data, the codifying comprising using natural language understanding (NLU) to normalize content of the observation data into categories;
• identifying, by a content identification module executing on the processor, overlapping content of the observation data and a base electronic document, the content identification module trained using training data that includes user feedback on overlapping contents previously identified by the content identification module, the identifying comprising comparing the codified observation data to a codified base electronic document that comprises content of the base electronic document normalized into the categories;
• comparing, by the processor, an order of the overlapping content in the observation data to an order of the overlapping content in the base electronic document;
• and
• changing, by the processor, an order of content in the base electronic document to create a modified electronic document based at least in part on the order of the overlapping content in the observation data being different than the order of the overlapping content in the base electronic document, wherein the modified electronic document comprises an index of entries that point to portions of the base electronic document.

A computer program product comprising a non-transitory computer-readable storage medium having program instructions embodied therewith, the program instructions executable by one or more processors to cause the one or more processors to perform operations comprising:

• receiving, by a processor, observation data about an activity;
• codifying the observation data to create codified observation data, the codifying comprising using natural language understanding (NLU) to normalize content of the observation data into categories;
• identifying, by a content identification module executing on the processor, overlapping content of the observation data and a base electronic document, the content identification module trained using training data that includes user feedback on overlapping contents previously identified by the content identification module, the identifying comprising comparing the codified observation data to a codified base electronic document that comprises content of the base electronic document normalized into the categories;
• comparing, by the processor, an order of the overlapping content in the observation data to an order of the overlapping content in the base electronic document;
• and
• changing, by the processor, an order of content in the base electronic document to create a modified electronic document based at least in part on the order of the overlapping content in the observation data being different than the order of the overlapping content in the base electronic document, wherein the modified electronic document comprises an index of entries that point to portions of the base electronic document.