System and method for automated course individualization via learning behaviors and natural language processing

Abstract

A system and method to optimize learning efficacy and efficiency in an online course is disclosed. In particular, the methods include customizing the sequence of delivery of course content as the course is being delivered, in a way that does not necessitate upfront input from an instructor/author or anyone else, beyond what which would be provided for a standard, non-adaptive course already. The present invention is also directed to a system to implement said customization and individualization methods. The present method is further directed to a linear flow of delivered materials, but the flow is dependent upon student actions in the course, among other conditions. In the present invention, individualized adaptation is based on this input, but can be augmented with additional information provided by instructors, if desired, as well.

1 . Using a processor-based computing system with communication access to a plurality of computing and structurable memory storage devices, a method for sequentially delivering modularized course content customized to a student based on the student's actions and determined proficiency, comprising the steps of:
 storing a library of content modules, each said module including elements tagged with identifying information relative to a specific learning feature;   electronically delivering a content module from said library to a student;   tracking said student's behaviors relative to interaction with said content module;   determining said student's proficiency related to at least one specific learning feature based on comparing tracked student behavior, including frequency of appearance of tagged content, to entries stored in at least one of said storage devices, said entries including behaviors related to proficiencies; and   delivering a next content module based on determined student proficiency.   
     
     
         2 . The method of  claim 1 , wherein said student behaviors are comprised of student actions and associated time stamps relative to at least one of video watching and text reading, said actions including mouse clicks and mouse movements and on screen locations of said clicks and movements. 
     
     
         3 . The method of  claim 2 , wherein said behaviors are used to calculate performance analytics. 
     
     
         4 . The method of  claim 3 , wherein determination of the next module for delivery is based on student behavior analytics related to a selected learning feature. 
     
     
         5 . The method of  claim 3 , wherein said next module selected for delivery is determined by comparing said analytics with stored comparable analytics related to other students. 
     
     
         6 . The method of  claim 3 , wherein delivery of said next module is determined element by element, and the next element is selected based on said determined student proficiency, determined as the student progresses in a module. 
     
     
         7 . A system for delivering a sequence of lessons online to a student comprising:
 a data base comprising a library of course lessons, each including content tagged by at least type or keyword and each tag associated with a learning feature;   a processor-based server for on-goingly determining a sequence of lessons to deliver to the student, based on student proficiency; and   a computing device including a graphical user interface for student viewing;   wherein lessons are delivered by element to said student for interaction using said interface, said processor selects each lesson for delivery based on determined student proficiency, said proficiency determined at least in part based on tracked student video-watching and text-reading behaviors.   
     
     
         8 . The system of  claim 7 , wherein each said lesson includes multiple elements, each element corresponds to at least one specific learning feature, and the next element in the lesson for delivery is selected based on student proficiency, determined using said tracked behaviors as the student progresses in the course. 
     
     
         9 . The system of  claim 8 , wherein said tracked student behaviors include student actions and associated timestamps, and actions include mouse clicks and mouse movements. 
     
     
         10 . The system of  claim 9 , wherein said proficiency is determined relative to a specific learning feature. 
     
     
         11 . The system of  claim 7 , wherein determination of the next lesson for delivery is based on student behavior analytics related to a selected learning feature. 
     
     
         12 . The system of  claim 11 , wherein said tracked student behaviors include student actions and associated timestamps, and the next lesson for delivery is determined by comparing said analytics with analytics related to other users. 
     
     
         13 . The method of  claim 7 , wherein said proficiency is based on comparing behaviors and proficiencies to those of other students. 
     
     
         14 . The method of  claim 7 , wherein said tracked student video-watching and text-reading behaviors include student actions and associated timestamps. 
     
     
         15 . A method for a computing system including structurable memory storage in a data store, a graphical user interface, and a processor, to deliver a customized course progression to a student based on determined student proficiency in said course comprising the steps of:
 forming a library of content items in said data store, said items indexed by a unique identifier corresponding to a specific learning feature;   forming aggregations of said content items in said storage, said aggregations arranged based on at least one element of learning style, topic, and level of difficulty;   creating a mapping between said aggregations, said mapping based on at least one of topical progression and degree of difficulty;   delivering one of said aggregations to said interface for interaction by a student;   assessing said student's performance of learning the content in the delivered aggregation based on tracked student behaviors including captured student actions, including clicks and other mouse movements during video-watching and text-reading behaviors as well as times between said actions, as they relate to specific learning features; and   using said assessment to determine the next aggregation to deliver to said student.   
     
     
         16 . The method of  claim 15 , wherein the next aggregation for delivery is determined based on a combination of said actions and times between actions and a comparison with actions and times between actions stored in said data store. 
     
     
         17 . The method of  claim 15 , wherein the next aggregation selected for delivery is determined by comparing analytics based on said behaviors with comparable analytics related to other users. 
     
     
         18 . The method of  claim 15 , wherein the next aggregation for delivery is selected based on said performance, determined as the student progresses in the delivered aggregation. 
     
     
         19 . The method of  claim 18 , wherein said performance is determined relative to a specific learning feature. 
     
     
         20 . The method of  claim 15 , wherein said mapping includes vectors indicating transition between aggregations and used in comparison to analytics of said student's behaviors so as to determine the next aggregation for delivery.