GroupLens Paper on New Users Selected as ACM IUI 2020 Most Impactful Paper
Professor Joseph Konstan and the GroupLens research lab will be recognized with the Most Impactful Paper award at the 2020 Association for Computing Machinery Intelligent User Interfaces (ACM IUI) conference.
Since 2017, the IUI steering committee has acknowledged past IUI papers that had significant impact and visibility since being published. The winning GroupLens research, Getting to Know You: Learning New User Preferences in Recommender Systems, was originally presented at the 7th annual IUI conference in 2002.
In the paper, Konstan, CS&E Professor John Riedl*, CS&E alumni Al Mamunur Rashid, Dan Cosley, Shyong Lam, and Sean McNee, and former Research Scientist Istvan Albert studied six techniques that collaborative filtering recommender systems can use to learn about new users. This work examined a variety of different strategies for eliciting preferences, ultimately showing that a successful approach had to balance popularity (the likelihood of having an opinion) with entropy (the degree to which opinions on the item differ).
Konstan recalled that this paper reshaped not only the MovieLens system, but also the way other systems chose items to prompt users for opinions. “Indeed,” he said, “that model survived in MovieLens for more than a decade before it was improved upon in a 2015 research paper.”
The award will be given during the ACM IUI conference in Cagliari, Italy in March 2020.
Congratulations to Professor Konstan and GroupLens on this tremendous recognition.
About ACM IUI
ACM IUI is the annual meeting of the intelligent interfaces community and serves as a premier international forum for reporting outstanding research and development on intelligent user interfaces. ACM IUI is where the Human-Computer Interaction (HCI) community meets the Artificial Intelligence (AI) community.