Learning Analytics Course Overview

Introduction

• Course Duration: 2 weeks
• Instructor: Professor from the Education Technology Department, IIT Bombay
• Prerequisites: No prior knowledge required; similar content to the previous course on Learning Analytics available.

Importance of Data in Education

• Rapid data generation by users on platforms like Facebook (1.56 billion monthly users) and Instagram.
• Organizations leverage data to understand user behavior (e.g., Netflix recommendations based on viewing habits).
• Similar patterns apply in e-commerce (e.g., Amazon product recommendations) and healthcare (using DNA and medical data).
• Learning data is generated through various digital tools:
  • Learning Management Systems (e.g., Blackboard, Moodle)
  • Educational apps (e.g., Google Classroom)
  • MOOCs (e.g., Coursera, MIT courses)

Learning Analytics Definition

• Learning Analytics: The measurement, collection, analysis, and reporting of data about learners and their context to improve learning outcomes.
• Core Purpose: Understand the learning process and enhance it.
• Key Components:
  • Data Collection: What data to collect and how.
  • Data Analysis: What to look for in the data.
  • Reporting: How to present findings to stakeholders (e.g., educators, students, administrators).

Role of Stakeholders

• Educators: Gain real-time insights into student performance, identify at-risk students, and tailor teaching strategies.
• Students: Receive performance comparisons with peers, fostering motivation and self-awareness of progress.
• Administrators: Use data to make informed decisions about course offerings and resource allocation.

Course Outline

Week 1: Introduction to Learning Analytics

• Understanding the relationship between Learning Analytics and Educational Data Mining.
• Discuss levels of Learning Analytics with examples.

Week 2: Data Collection and Pre-processing

• Key focus on what data to collect in various environments.
• Introduction to Daybreaker tool (open source) for data analysis.
• Overview of ethics and data privacy in data collection.
• Quiz on data pre-processing.

Week 3: Basics of Machine Learning

• Introduction to supervised and unsupervised learning.
• Metrics for evaluating machine learning algorithms.
• Introduction to the Orange tool for data analysis (available for academic use).

Week 4: Descriptive Analytics

• Techniques for describing data using Excel and Google Sheets.
• Introduction to ISET tool for visualization and diagnostics.

Week 5: Diagnostic Analytics

• Understanding correlation and regression analytics.

Week 6: Sequential Pattern Mining and Process Mining

• Tools for sequential pattern mining and process mining (e.g., Pro-AML tool).

Week 7: Predictive Analytics

• Feature selection and linear regression using Daybreaker tool.

Week 8: Decision Trees

• Explanation of decision trees using Orange tool.
• Introduction to Naive Bayes algorithm.

Week 9: Unsupervised Machine Learning

• Overview of clustering techniques.

Week 10: Text Analytics and Natural Language Processing

• Application of text analytics for grading essays.
• Introduction to word embeddings in NLP.

Week 11: Multimodal Learning Analytics

• Collecting data from multiple sensors (e.g., eye trackers, webcams).

Week 12: Advanced Topics in Learning Analytics

• Discussion of advanced topics based on recent research and conferences.

Conclusion

• Emphasis on the importance of collecting and analyzing data for improving student learning outcomes.
• Encouragement to explore the field further through textbooks and research articles.