CMU logo

Special Topics: LEADS Learning Analytics and Educational Data Science

Course Information

Course Number

HCI Undergraduate: 05-499 B
HCI Graduate: 05-899 B

Course Description

This course provides students with a foundational understanding of the principles, methods, and tools used in learning analytics. This course is for advanced undergraduate students and graduate students interested in using data and analytic tools to derive insights for practice, especially, but not limited, to educational practice. Students will explore how data can be collected, analyzed, and interpreted to gain insights into student learning behaviors, improve learning outcomes, and inform instructional practices. The course will be run as a combination of discussion seminars and labs involving hands-on practice of skills such as Classifiers, IRT models, Regression, Feature Engineering, and GenAI.

Key Topics
The course involves discussion and hands-on practice of core research skills necessary for deriving actionable insights from educational data. The course covers key concepts such as data mining, predictive modeling, and data visualization, with a focus on practical applications in educational settings.

Prerequisite Knowledge
Basic knowledge of statistics (e.g., introductory linear regression, probability) and/or basic programming (e.g., proficiency in R or Python for data analysis).

Course Goals 
By the end of the course, students will (1) be able to implement and evaluate common educational data science models (e.g., Classifiers, IRT, Regression) using R or Python, and (2) will be able to critically assess the ethical and equity implications of using learning analytics in practice.

Assessment Structure
The class is broken up into modules, each involving one focal learning analytics of educational data/data science method. Students are assigned readings (research papers, book chapters, editorials, etc.) to prepare for the class session and homework assignments that provide direct experience with the research methods they learn and analyzing data that they collect in executing those methods. In the class itself, there are reviews of readings, lectures, demonstrations, and discussions and critiqued presentations by students. The work in the class consists of individual work: (a) readings before class (b) homework assignments, (c) hands-on research practice activities, and (d) a semester project. We discuss the readings each week, and students are graded on their contribution to this discussion. Minimal credit is given for showing up for class; more credit is given for active class participation.

Learning Resources
Students will use a variety of learning resources to improve their skills including required textbooks, published research articles, method tutorials, and statistical analysis software (R or Python).

Extra Time Commitments
Assignments, readings and the semester project for this course are done outside of class, but should fit within typical expectations based on the number of units of credit.

Semester Offered and Units

Semester: Spring 2027
Undergraduate: 12 units
Graduate: 12 units

Instructor(s)

Michael Asher