Joseph Konstan to Lead $2 Million NSF Grant to Study Human-Centered AI for News Recommender Systems

Department of Computer Science & Engineering professor Joseph Konstan will lead a new $2 million research project studying human-centered artificial intelligence (AI) for a shared news recommender system. The project titled, “A Research News Recommender Infrastructure with Live Users for Algorithm and Interface Experimentation”,  is part of a $16.1 million investment from the U.S. National Science Foundation’s (NSF) Computer and Information Science and Engineering (CISE) directorate. Funding aims to support shared research infrastructure for AI researchers and students. 

The University of Minnesota’s project is part of NSF's Computer and Information Science and Engineering Community Research Infrastructure (CCRI) program, which seeks to create, enhance and democratize access to research infrastructures, focusing on scientific agendas across computer and information science and engineering. The U of M is one of five collaborative projects supported by the NSF CCRI investment.

Led by Konstan, the shared news recommender system aims to enable researchers nationwide to carry out live one-time and longitudinal experiences on users of AI systems that personalize the news-reading experience. This project grows out of Konstan’s 25-year history of running MovieLens, an experimental news recommender system that has had hundreds of thousands of users and has been used for over a hundred experiments.  

“We’ve been leaders in recommender systems research for decades, because we’ve had the ability to run live experiments when many others were limited to simulating systems using collected datasets,” said Konstan. “This is our chance to bring the power of experimentation to the broader research community.”    

Recommender systems have extraordinarily broad impact through, for example, the products ranked and shown to an online shopper based on past shopping behaviors. Recommender systems are also behind most online news sources, and can shape which news people see. Given the importance of these systems, it is critical for researchers to be able to carry out studies to evaluate different algorithm and interface designs and their impact on users.

"A critical element to the success of the AI research revolution is ensuring that researchers have access to the data and platforms required to continue to drive innovation and scalability in AI technologies and systems," said NSF Director Sethuraman Panchanathan. "This infrastructure must be accessible to a full breadth and diversity of talent interested in AI research and development, as that is the driving force behind modern discoveries."

This project will be conducted in collaboration with University of Colorado Boulder, Boise State University, Northwestern University, and Clemson University. For more information, visit the NSF CCRI website.

The other collaborative projects awarded grants by NSF’s CCRI program are led by the University of Central Florida; the University of Pennsylvania; the University of California Los Angeles; and Pennsylvania State University.

For more information on the other projects, read the full NSF news release