Robin Burke

Robin Burke photo

I am a professor in the Department of Information (and Computer Science, by courtesy) at the University of Colorado, Boulder and the director of That Recommender Systems Lab. I was previously co-director of the Web Intelligence Lab in the School of Computing at DePaul University.

I earned my PhD in Computer Science in 1993 at Northwestern University's Institute for the Learning Sciences, under the supervision of Dr. Roger Schank, and before DePaul, worked at the University of Chicago, the University of California Irvine, California State University Fullerton, and the long-gone dot-com startup Verb.

See complete CV.


I conduct research mostly in recommender systems and personalization, more generally. Recently, I have been interested in two closely-related topics:

I am also interested in practical problems of conducting recommender systems research and achieving replicable results.

In addition, I have research interests in the digital humanities and am part of the Reading Chicago Reading research group.


Fall 2019: INFO 4871/5871

Data Science for Information Science: Research in information science often requires gathering, managing, analyzing, processing, and understanding complex data. This course introduces tools from computing and statistics to develop students' skills in the following areas: (1) data wrangling, the process of acquiring, cleaning, reshaping, and/or sampling data; (2) data exploration and analysis, the extraction of meaningful signals in large, noisy datasets, especially data consisting of unstructured or semi-structured text and relational (network-oriented) data; (3) predictive modeling, the creation of models to support inferences and decisions based on data; and (4) communication, the summarization and visualization of findings to be shared with others.

Spring 2019: INFO 4871/5871

Recommender Systems: This is a research seminar that will explore the space of personalized information access applications known as recommender systems. This class will introduce students to a range of approaches for building recommender systems including collaborative, content-based, knowledge-based,and hybrid methods. Students will also explore a variety of applications for recommendation including consumer products, music, social media, and online advertising. The course will also examine controversies surrounding recommendation, including Pariser’s “filter bubble”, the deployment of personalization as a tool for electoral manipulation, and questions of algorithmic bias.


I have been conducting research in the area of recommender systems since the mid-1990s, and have been involved with the ACM Recommender Systems Conference since its founding. Since 2017, I am the chair of the steering committee for the conference.


Prospective PhD students, please see this FAQ file.