|
|
|
Step 1
An ePub Textbook or HTML files are loaded into our system.
|
Step 2
Algorithms automatically parse the text to identify the taxonomy and key learning concepts.
|
Step 3
Content experts use online tools to rank and refine the key concepts.
|
Step 4
The system parses the text again, identifying thousands of potential questions.
|
|
|
Access a Large Library of Test Items for OER Textbooks
As a proving ground for the Items2 process, we are currently developing tens of thousands of quality items for top OER textbooks. If you are in need of assessment items for specific OER texts, we'd love to work with you. |
|
Rigor & Relevance
Our AI algorithms generate test items based on pedagogical best practices. Items are derived directly from textbooks or online course material, but are enhanced by data found on the Internet. All test items go through a rigorous review process, ensuring quality, rigor and end-to-end coverage of the learning material.
|
|
Example Identification - Drag-and-Drop
In this problem-type, Items Squared algorithms identify examples or case-studies from the text based on key learning concepts. The student then matches the key learning concept to the example.
Figure Concept Identification - Drag-and-Drop
In this problem-type, Items Squared identifies all figures within a text that contain key learning concepts. Students drag and drop the key learning concepts into the appropriate place on the figure.
Example - Multiple-Choice
In this problem-type, Items Squared identifies examples or case studies within the text that relate to key learning concepts. The AI then identifies distractors that are like in context, similar in length, plausible and mutually exclusive. Students identify the key learning concept described in the example.
Key Concept - Multiple-Choice
In this problem-type, Items Squared identifies passages within the text that contain key learning concepts. The key learning concept is removed from the sentence as the correct answer. The AI then identifies distractors that are like in context, similar in length, plausible and mutually exclusive. Students choose the correct key concept from the options provided.
Important People - Multiple-Choice
In this problem-type, Items Squared identifies passages within the text that mention important people. The important person's name is removed from the passage as the correct answer. The AI then searches the text and various Internet resources for similar types of people to use as distractors. In the example below, psychiatrist Leo Kanner is the important person. The distractors are all other well-known psychiatrists.
Timeline - Multiple-Choice
In this problem-type, Items Squared extracts phrases where important dates or references to time are used relative to key learning concepts from the source text. The date or time is removed from the passage as the correct answer. Items squared then uses artificial intelligence to create distractors that are similar dates or times.
What's up Next - R&D
Compare and Contrast - Drag-and-Drop
In this problem-type, a subject matter expert identifies two learning concepts for students to compare and contrast. The Items Squared AI will then automatically search the text and various Internet sources for attributes of each of the learning concepts. The subject matter expert chooses which of the attributes should go in each box. Students drag and drop the attributes into the correct area.
Process Steps - Rubric
In this problem-type, Items Squared identifies a sequential process related to key learning concepts within the text. It then identifies steps of the process. The subject matter expert ensures that the steps are all represented and in the right order. The student drags the steps in the right order.
Rating Ordered Steps or Components based on a Rubric - Multiple-Choice
This problem-type uses a series of ordered steps in a process or a series of components related to a key concept. The AI scrambles the steps and/or their descriptions. The student then rates the explanation based on a rubric.
