Projects and project information listed in the table are retrieved from the Artificial Intelligence For Education page maintained and updated by NIE's Learning Sciences and Assessment Department.
| Project Name | Project Developer/ PI | Project Description |
|---|---|---|
| NIE x RI collab on generative AI for STEM assessment | Ast/P Farhan Ali Ast/P Joonhyeong Park Mr Kuang-Wen Chan |
This project comprehensively assesses large language models for their capabilities in generating advanced high school assessment items in various STEM subjects. |
| TeacherGAIA | Ast/P Farhan Ali | TeacherGAIA is a generative-AI chatbot developed by LSA to support diverse forms of student-centered learning. It is currently in use in numerous MOE schools with free accounts for teachers and students. |
| AI-Empowered Analytics on Gesture | A/P Chen Wenli Ms Lyu Qianru |
This research explores how students apply bodily engagement for computer-supported collaborative learning (CSCL). We have utilized MediaPipe, a machine learning model, to analyze video files and extract moment-by-moment body landmarks. This approach allows us to understand and visualize how students use hand movements and body gestures during collaborative learning activities. |
| AI-Empowered Analytics on Joint Attention | A/P Chen Wenli Ms Lyu Qianru |
This research examines how students apply joint attention, specifically synchronized gazing detection, for collaborative learning. By using machine learning models such as YOLOv7 for gazing detection and object detection, we analyze video files to capture moment-by-moment gazing and object detection. This method provides a precision level of 60% to 89%. |
| LLMs Chatbot Proof-of-Concepts | A/P Tan Seng Chee Ms Tan Yee Yin |
Six different proof-of-concepts chatbots that explore and exemplify teaching and learning from, with, about, and beyond AI. |
| ARCHE 2.0 | Ast/P Wen Yun | An AI-powered seamless Chinese vocabulary learning system for young learners. |
| Students' AI-Augmented Thinking, Academic Performance and Emotions During Problem Solving | Ast/P Zhu Gaoxia | This project aims to understand students’ thinking processes when programming with the supported of generative AI or not; and examine What factors will impact AI-augmented thinking? |
| Embodied Learning Companions as An Experimentation Platform for Scaffolding in the Learning Sciences | Ast/P Tanmay Sinha | Learning companions, implemented as 2-D/3-D virtual characters, can evoke trust with human-like shape and form (appearance realism). Provide multimodal adaptive support based on inferring multimodal student behaviors (behavior realism). |
| AARA-DA: AI Powered Avatar, Adaptive Progression and Remediation Analytics for Dyscalculia | Ast/P Azilawati Jamaludin Dr Lim Choon Guan |
AARA-DA is a neuroscience-informed mathematics Fractions games powered by a VR teacher/caregiver avatar that is trained to provide personalized cognitive and affective care for learners between the ages of 7 - 13. |
| An Investigation on the Efficacy of Redesigning Learning Assessments with Gen AI | Dr. Kumaran Rajaram Ast/P Tanmay Sinha |
The project aims to develop innovative formative assessments that use genAI to provide deliberate critiquing opportunities for students and assess their impact on learning across interdisciplinary courses at NBS and NIE. |
| Does the Teacher Matter? University Students’ Physiological Responses in Online Interactions with an AI-Chatbot and a Human Teacher | Ast/P Victor Lim Fei | The study aims to explore how students respond to the use of generative AI by examining potential differences in students’ levels of interest, measured through emotional arousal, when communicating with an AI bot versus a human to learn about a new topic. The findings will inform effective AI integration in educational settings to enhance learning outcomes. |
| Open emotion learner modeling to improve machine predictions and improve human metacognition |
Ast/P Tanmay Sinha
|
The project aims to kill two birds with one stone – improve emotionally-aware AI as well as students’ self-regulated learning – by creating open learner models (OLMs) where emotional predictions can be refined with human feedback. Different interaction designs for OLMs to enhance emotional awareness and regulation in education will be tested. |