Adaptive Learning with Automated Doubt Mining and Topic Alignment

Project Description

This TEL project focuses on adaptive and personalized learning and teaching comprising three components: (1) deriving analysis models for evaluating topic alignment, (2) identifying doubts (misalignment) and (3) a personalized quiz recommender which uses adaptively serve relevant questions to individual student based on how well his/her alignment is to the topics taught e.g. if a student has higher alignment in Topic 1 and higher misalignment in Topic 2, he/she will be served more practice questions for Topic 2. The aim of the game is for each individual player, who is now a team leader, to grapple with the complexities of the given situation, including the team members’ varied personalities. He/she has to manage the team well to get out of the present predicament.

Teaching Strategy

As effective teaching is to enable effective learning, this project aims to address the needs for each individual student through monitoring the progress of the students and providing timely feedback.

Students are given the opportunity to reflect on their learning after class by penning down reflections and key learning points for the week. The reflections make significant impacts in their learning in two ways. Firstly, students revised the topics before filing the reflection and secondly, students take the opportunity to validate their learning by spontaneously writing their thoughts, doubts and questions in the reflections.

 

Instead of having instructors to read these reflections and identify the learner’s concerns take time resulting to delayed feedback to the learners, this project collectively processes learners’ concerns and objectively categorises the different subtopics and identifies the misalignment to address for each session as well as dishes out quiz questions based on students’ needs.

 

For access to the project, please contact Centre for Teaching Excellence at cte [at] smu.edu.sg

Faculty:

  • Associate Professor Tan Kar Way
  • Assistant Professor Ouh Eng Lieh
  • Assistant Professor Lo Siaw Ling

Project Type:

Adaptive Digital Tools

School:

SCIS

Pedagogy:

Personalised Learning