SLS module: Moving Beyond a Standalone Simulation: Building an AI-Supported Learning Experience in SLS

 https://vle.learning.moe.edu.sg/community-gallery/module/view/23a1f139-6abc-421e-8244-c677223a4183

This SLS module https://vle.learning.moe.edu.sg/community-gallery/module/view/23a1f139-6abc-421e-8244-c677223a4183 demonstrates how an interactive simulation can be developed into a more complete learning experience—one that supports students before, during and after their exploration.

A key addition is the video tutorial https://www.youtube.com/watch?v=kCyH0USh7T0, which introduces students to the simulation and demonstrates how its controls should be used. This reduces the time students spend figuring out the interface and allows them to focus more quickly on the intended scientific concepts and relationships.

The simulation itself provides students with an environment in which they can manipulate variables, observe changes and test their ideas. Rather than simply watching an animation, students learn through purposeful interaction and experimentation.

One of the most significant enhancements is the addition of a scorable component. Selected student actions within the simulation are captured and evaluated, allowing the system to provide targeted feedback based on what each student actually did.

The feedback can therefore address specific choices, patterns of interaction or possible misconceptions instead of giving every student the same generic response.

The simulation also produces two complementary forms of learning evidence:

• Quiz analytics show whether students answered the embedded questions correctly and help identify commonly held misconceptions.
  
  
  
• Time-stream interaction data records how students engaged with the simulation over time, providing a more detailed picture of the sequence and timing of their actions.
  
  
  

Together, these data sources allow teachers to look beyond the final score. Teachers can examine not only whether a student reached the correct answer, but also how the student explored the simulation, what decisions were made and where the student might have encountered difficulty.

The remaining questions make use of SLS Short Answer Feedback. Here, the native SLS AI capability is harnessed to interpret students’ written responses and provide timely, targeted feedback. This enables students to articulate their reasoning in their own words while still receiving individualised guidance without requiring the teacher to mark every response immediately.

The overall module therefore brings together several layers of support:

1. Video guidance to help students begin.
2. Interactive exploration to make thinking and experimentation visible.
3. Scorable interactions that provide targeted feedback.
4. Quiz analytics that reveal achievement and common errors.
5. Time-stream data that captures students’ learning processes.
6. AI-supported short-answer feedback that responds to students’ explanations.

The important innovation is not any single feature. It is the way the different components work together. The module combines instructional scaffolding, interactive exploration, assessment, learning analytics and AI-supported feedback within one SLS learning experience.

This creates a useful model for future SLS resources: a simulation should not function merely as a digital demonstration. When thoughtfully designed, it can become an evidence-generating formative assessment environment that helps students learn while also giving teachers meaningful insight into their thinking.

Email version

Subject: Enhanced SLS simulation module with targeted feedback and learning analytics

Dear colleagues,

I would like to share several enhancements that have been incorporated into this SLS module.

The module now includes a video tutorial that introduces students to the simulation and explains how to use its controls. This helps students begin their exploration more independently and focus on the intended learning rather than the operation of the interface.

The simulation also includes a scorable component that evaluates selected student interactions and provides targeted feedback based on what each student actually does. This allows the feedback to address specific actions and possible misconceptions instead of relying only on a final correct or incorrect answer.

Teachers can access two complementary forms of evidence:

• Quiz analytics, showing students’ responses and performance.
• Time-stream data, showing the sequence and timing of students’ interactions with the simulation.

The remaining constructed-response questions use SLS Short Answer Feedback. This harnesses SLS’s native AI capability to interpret students’ written answers and provide timely, targeted feedback on their reasoning.

Overall, the module integrates video scaffolding, interactive exploration, scorable assessment, learning analytics and AI-supported feedback. It is designed not only to engage students in a simulation, but also to make their learning processes more visible and support teachers in identifying misconceptions and planning follow-up instruction.