Researchers have designed an artificial intelligence (AI) model that is better able to predict how much students are learning in educational games.
The improved model makes use of an AI training concept called multi-task learning, and could be used to improve both instruction and learning outcomes.
Multi-task learning is an approach in which one model is asked to perform multiple tasks.
“In our case, we wanted the model to be able to predict whether a student would answer each question on a test correctly, based on the student’s behavior while playing an educational game called Crystal Island,” says Jonathan Rowe, co-author of a paper on the work and a research scientist in North Carolina State University’s Center for Educational Informatics (CEI).
“The standard approach for solving this problem looks only at overall test score, viewing the test as one task,” Rowe says. “In the context of our multi-task learning framework, the model has 17 tasks – because the test has 17 questions.”
The researchers had gameplay and testing data from 181 students. The AI could look at each student’s gameplay and at how each student answered Question 1 on the test. By identifying common behaviors of students who answered Question 1 correctly, and common behaviors of students who got Question 1 wrong, the AI could determine how a new student would answer Question 1.
This function is performed for every question at the same time; the gameplay being reviewed for a given student is the same, but the AI looks at that behavior in the context of Question 2, Question 3, and so on.
And this multi-task approach made a difference. The researchers found that the multi-task model was about 10 percent more accurate than other models that relied on conventional AI training methods.
“We envision this type of model being used in a couple of ways that can benefit students,” says Michael Geden, first author of the paper and a postdoctoral researcher at NC State. “It could be used to notify teachers when a student’s gameplay suggests the student may need additional instruction. It could also be used to facilitate adaptive gameplay features in the game itself. For example, altering a storyline in order to revisit the concepts that a student is struggling with.
“Psychology has long recognized that different questions have different values,” Geden says. “Our work here takes an interdisciplinary approach that marries this aspect of psychology with deep learning and machine learning approaches to AI.”
“This also opens the door to incorporating more complex modeling techniques into educational software – particularly educational software that adapts to the needs of the student,” says Andrew Emerson, co-author of the paper and a Ph.D. student at NC State.
The paper, “Predictive Student Modeling in Educational Games with Multi-Task Learning,” will be presented at the 34th AAAI Conference on Artificial Intelligence, being held Feb. 7-12 in New York, N.Y. The paper was co-authored by James Lester, Distinguished University Professor of Computer Science and director of CEI at NC State; and by Roger Azevedo of the University of Central Florida.
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
Multi-task learning
- Here's how the Army's Multidomain Task Force is contributing to AUKUS
The U.S. Army's 3rd Multidomain Task Force, headquartered in Hawaii, is getting officers from both Australia and the U.K. this summer and will work on advancing technology that's. focus of the second ...
- Here's how the US Army's multidomain task force is contributing to AUKUS
The 3rd Multidomain Task Force is collaborating with Australia and the U.K. to develop technology like artificial intelligence and machine learning.
- Abortion foes, supporters say Texas maternal death task force should review abortion cases
A sponsor of a Texas law that has prohibited the state's maternal death task force from reviewing abortion records ... the policies they have lobbied for — are also interested in learning more about ...
- Insilico Medicine introduces nach0: A one-stop LLM for chemical and biomedical tasks
The multi-domain and multi-task LLM was trained on a diverse set of tasks, natural language understanding, synthetic route prediction, and molecular generation, and works across domains to answer ...
- MIT Creates Shape-Shifting Slime Robots Powered by Machine Learning Technique
MIT researchers have introduced a new algorithm designed to facilitate the creation of shape-shifting slime robots using a machine learning technique.
Go deeper with Google Headlines on:
Multi-task learning
[google_news title=”” keyword=”multi-task learning” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]
Go deeper with Bing News on:
AI predictive model
- 4 Ways Agencies Are Paving the Way for Generative AI
Horowitz is a seasoned tech journalist and copy editor with 25 years of experience. As agencies prepare to increase adoption of generative artificial intelligence, they will need to simplify how they ...
- VA is already using AI to identify and assist veterans in crisis, officials say
“was originally a statistical model and now has become an AI.” REACH VET first began as a pilot program in 2016 and used a predictive algorithm to identify veterans who are in the top 0.1% tier of ...
- Multifamily Housing and AI: How Predictive Tools Save Owners Time and Money
There’s only time to grab a few essential items and hope firefighters can contain the flames before they engulf all your worldly possessions. This was the ordeal faced by nearly 200 residents at Avana ...
- mPulse Launches New Predictive Analytics and Engagement Solution and Reports Strong Q1 2024 Growth
Pulse, a leader in conversational AI and digital engagement solutions for the healthcare industry, today announced strong momentum in Q1 2024 over Q1 2023 with growth across all business segments. The ...
- AI: The missing link for hitting transport net-zero targets?
Herman Scheepers, considers opportunities offered by AI in supporting the transport sector’s transition to greener energy ...
Go deeper with Google Headlines on:
AI predictive model
[google_news title=”” keyword=”AI predictive model” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]