Educational and content recommendation management system
A method of delivering educational content to a user includes accessing a first content item of a plurality of content items based on a knowledge base, where the knowledge base includes a graph structure with a plurality of nodes associated with the plurality of content items. The method further includes providing the first content item to a user on a display and receiving one or more user assessment variables based on a response of the user to the first content item. A second content item of the plurality of content items is recommended based on the one or more user assessment variables and the knowledge base. The method further includes accessing the second content item recommended by the node and displaying the second content item of the display.
1 . A method of delivering educational content to a user, the method comprising:
accessing a first content item of a plurality of content items based on a knowledge base, the knowledge base including a graph structure with a plurality of nodes associated with the plurality of content items;
providing the first content item to a user on a display;
receiving one or more user assessment variables based on a response of the user to the first content item;
generating a user model based on the one or more user assessment variables;
determining a node in the knowledge base by using the user model to navigate the knowledge base;
recommending a second content item of the plurality of content items based on the node in the knowledge base;
accessing the second content item represented by the node; and
displaying the second content item on the display.
2 . The method of claim 1 , wherein the plurality of content items are stored in a content database, the method further comprising:
accessing the content database to generate the knowledge base based on the content database.
3 . The method of claim 2 , further comprising:
accessing the plurality of content items from the content database;
forming a corpus based on the plurality of content items;
generating a probability model of the content items; and
using the probability model to generate the knowledge base by:
generating one or more of the plurality of nodes of the knowledge base, each node of the plurality of nodes representing a topic; and
generating edges amongst the plurality of nodes of the graph structure, each edge connecting a respective first node and second node of the plurality of nodes, each edge including a weight representing a probability of the respective first node and second node belonging to a same concept.
4 . The method of claim 3 , wherein the probability model is a latent Dirichlet allocation (LDA) model.
5 . The method of claim 1 , wherein recommending the second content item further comprises:
determining the second content item from a plurality of candidate content items, wherein the second content item is associated with a maximum probability of success among the candidate content items, and wherein the probability of success associated with a respective content item represents a probability that the user will respond to the respective content item correctly.
6 . The method of claim 1 , wherein the first content item is a portion of a video segment, the method further comprising:
determining one or more concepts within the video segment; and
mapping a concept of the one or more concepts to a time interval of the video segment, wherein the time interval of the video segment defines the portion of the video segment.
7 . The method of claim 6 , wherein the first content item is associated with the concept, wherein accessing the first content item comprises accessing the portion of the video segment based on the time interval mapped to the concept.
8 . A recommender system comprising:
a processing device; and
computer readable medium containing programming instructions that, when executed, will cause the processing device to:
access a knowledge base;
obtain one or more user assessment variables;
generate a user model based on the one or more user assessment variables;
use the user model to navigate the knowledge base to determine a node in the knowledge base;
access a content item represented by the determined node; and
recommend the content item for display to a user device;
update the user model based on an input from a user associated with the user device;
navigating the knowledge base to determine a second node based on the user model;
access a second item represented by the second node; and
present the second content item to the user device.
9 . The recommender system of claim 8 , wherein the knowledge base includes a graph structure with a plurality of nodes including the node, the plurality of nodes representing a plurality of content items including the content item.
10 . The recommender system of claim 9 , wherein the graph structure further includes edges amongst the plurality of nodes of the graph structure, wherein each edge connects a respective first node and second node of the plurality of nodes, each edge including a weight representing a probability of the respective first node and second node belonging to the same concept.
11 . The recommender system of claim 8 , wherein the user model is a model of a state of the user, the state of the user including a plurality of states corresponding to the user assessment variables.
12 . The recommender system of claim 8 , wherein updating the user model based on the input from the user associated with the user device comprises:
presenting the content item to the user device; and
updating the user model based on input from the user while the content item is presented to the user device.
13 . The recommender system of claim 12 , wherein the instructions further cause the processing element to update the user model based on one or more engagement characteristics detected from the input from the user while the user engages with the content item.
14 . The method of claim 1 , wherein the user model is a model of a state of the user, the state of the user including a plurality of states corresponding to the user assessment variables.
15 . A recommender system comprising:
a processing device; and
computer readable medium containing programming instructions that, when executed, will cause the processing device to:
access a knowledge base;
obtain one or more user assessment variables;
generate a user model based on the one or more user assessment variables, wherein the user model is a model of a state of a user, the state of the user including a plurality of states corresponding to the user assessment variables;
use the user model to navigate the knowledge base to determine a node in the knowledge base;
access a content item represented by the determined node;
recommend the content item;
present the content item to a user device associated with the user;
update the user model based on input from the user while the content item is presented to the user device;
use the updated user model to navigate the knowledge base to determine a second node in the knowledge base;
access a second item represented by the second node; and
present the second content item to the user device.
16 . A method of delivering educational content to a user, the method comprising:
displaying, at a user interface, a first content item of a plurality of content items, the first content item being represented by a first node of a plurality of nodes in a knowledge base, the plurality of nodes in the knowledge base representing the plurality of content items;
determining, from user input received at the user interface during the display of the first content item, one or more user assessment variables;
updating a user model using the one or more user assessment variables wherein the user model is representative of a user knowledge of concepts;
determining a second node of the plurality of nodes in the knowledge by using the updated user model to navigate the knowledge base; and
displaying, at the user interface, a second content item being represented by the second node.
17 . The method of claim 16 , wherein the input received at the user interface includes a reported confidence of the user in answering a question of the first content item.
18 . The method of claim 17 , wherein the reported confidence is provided via a slider provided at the user interface.
19 . The method of claim 16 , wherein the user model is further updated based on one or more engagement characteristics detected from the input from the user while the user engages with the content item.