Explore cutting-edge research on predicting student success in Massive Open Online Courses (MOOCs) through this 27-minute conference talk. Delve into the innovative application of meta transfer learning techniques for early success prediction in online education. Learn about the research objectives, pipeline, and methodologies employed, including feature extraction, classification, and the use of meta models. Discover how attention layers and fine-tuning contribute to improved predictions. Gain insights into the implications of this research for the future of online learning, and understand the data collection process and potential extensions of this work. Engage with the discussion on how deep learning approaches can enhance educational outcomes in MOOCs.
Meta Transfer Learning for Early Success Prediction in MOOCs
Association for Computing Machinery (ACM) via YouTube
Overview
Syllabus
Intro
Deep Learning has
Previous Work
Objectives
Research Questions
Pipeline
Feature Extraction
Classification
Baselines
Meta Models
RQ2: Attention Layers
Fine-tuning
Implications DISCUSSION
Extensions FUTURE WORK
Data Collection METHODOLOGY
Taught by
Association for Computing Machinery (ACM)
