Project 5
Project 5
LDT630
LDT630
Embedded Files
Project 5 Closing Learning Cycle
Project 5 Closing Learning Cycle
Generative AI tools such as ChatGPT brought a recent tech breakthrough everywhere, revolutionizing how we educate. In Project 4, we explored the concept of emerging trends in adaptive learning with machine learning and predictive analytics. To operationalize such an expansive personalized learning environment, we must pull data from learning analytics, including discourse, social learning, and semantic social network analytics. Based on the conceptual thinking and research on available resources, we wrote an op-ed article and created a new approach for personalized learning, adjusting to the individual learner's needs.
1. Design Document
1. Design Document
First, I evaluated the original course I created in the 400x course and identified areas of improvement using the OLC QCTIP scorecard.
Next, I applied the design framework from Project 4 and wrote the rationale for the suggested updates. Then, I prioritized an area of need, the most pressing leverage point, supported by data.
yamamotor-design document.pdf 2. Adaptive Module
2. Adaptive Module
To log in as a guest learner, please use the email and password provided.
https://canvas.instructure.com/login/canvas
Email: wagarden6@gmail.com
Password: LDTrytestuser
Follow the directions below.
Go to Re-creating Your Career v.2
2. Find Module #1 [Adaptive Learning Module] and Start here [Adaptive]
3. Please ensure you log out after viewing so another user can log in after you.
The Features of Adaptive Module
The Features of Adaptive Module
1. Just-in-time feedback function by integrating an external LTI app.
2. Pathways after Quiz 1 in Module 1.
3. AI chatbot in training.
I started the tutorial of Dialogflow, powered by Google Cloud. There will be a couple of steps—creating a chatbot, training a conversational flow related to the course, integrating the chatbot with Canvas LMS API, and testing the chatbot’s function—before deploying. It will take me a couple of months to appear the chatbot on Canvas LMS. I’ll take courses on AI foundation and work on it, but it cannot be available by the due date of the course.
4. Integrating separated data with xAPI from Google Form, Canvas, Padlet, and Piazza into an LRS.
At this point, I learned to manually send simple xAPI statements to an LRS, but I need to develop knowledge on syncing data conversion into JSON file format to store a stream of data in the LRS. I also need to know how the LRS and database work together and how to protect collected data. This is also a challenging project that will demand my time after the course.
The Process and Reflection
The Process and Reflection
Thinking process and workflow
Thinking process and workflow
Clarify the definition of adaptive learning because I saw no one agreed-on definition.
"Adaptive Learning" can describe pedagogy, tech-supported programs, or edTech products.
Using QCTIP to evaluate the original course.
Create a chart from the quantitative analysis, but I realized that the instructor's tasks would be redistributed with the AI assistant in the adaptive learning environment. The role needs to be clarified.
Extract the priority criteria from each section and find supporting data to produce suggestions.
Brainstorm what function can make the course adaptive.
Research adaptive courseware that can implement the suggestions, but most are geared toward large organizations.
Research CWiC Framework.
Research what students want from adaptive courseware.
Find what platform is available for an individual's practice.
Organize the brainstormed ideas into categories to know what I can realize with available time, resources, and skill level.
Decide to stay with the Canvas LMS and use branching scenario functions.
Link to an external LTI app to satisfy the area of need.
Add stretch and challenging functions.
Determine how much I can bring the suggestions into reality within a limited time.
In the end
The final project was the most thinking-consuming because creating adaptive learning is theoretically possible. Still, I have not yet developed the technical skills to code the backend to link AI and data. As a designer, it is important to make grounded suggestions that are implementable by the team members. I will continue learning about the backend to understand what it takes to create personalized adaptive courses.
References
Chen, X., Breslow, L., & DeBoer, J. (2018). Analyzing productive learning behaviors for students using immediate corrective feedback in a blended learning environment. Computers & Education, 117, 59–74. https://doi.org/10.1016/j.compedu.2017.09.013
Kennedy, P. E., Chyung, S. Y., Winiecki, D. J., & Brinkerhoff, R. O. (2014). Training professionals’ usage and understanding of Kirkpatrick’s Level 3 and Level 4 evaluations: Usage and understanding of Kirkpatrick’s level 3 and 4 evaluations. International Journal of Training and Development, 18(1), 1–21. https://doi.org/10.1111/ijtd.12023
O'Sullivan, P., Forgette, C., Monroe, S., & England, M. T. (2020). Student Perceptions of the Effectiveness of Adaptive Courseware for Learning. Current Issues in Emerging eLearning 7(1), 71-100. https://scholarworks.umb.edu/ciee/vol7/iss1/5
Seo, K., Tang, J., Roll, I., Fels, S., & Yoon, D. (2021). The impact of artificial intelligence on learner–instructor interaction in online learning. International Journal of Educational Technology in Higher Education, 18(1), 54. https://doi.org/10.1186/s41239-021-00292-9
Statistica. (n.d.). US hours of training per employee 2022. Statista. https://www.statista.com/statistics/795813/hours-of-training-per-employee-by-company-size-us/
Page updated
Google Sites
Report abuse