What is it about?
Group Recommender Systems (GRSs), i.e., systems that help groups to make choices, for instance, a destination to visit or a movie to watch together, have been studied and prototyped for more than twenty years. However, their practical application and usage has not flourished. As a result, the RSs that we all use now, are only targeted to individual users, when they are choosing an item exclusively for themselves. In this opinion article we discuss why the success of group recommender systems is lagging and we propose a research program unfolding on the analysis and development of new forms of collaboration between humans and intelligent systems. We define a set of functional roles, named CAJO, that GRSs should play in order to become more useful tools for group decision making.
Featured Image
Photo by Margarida CSilva on Unsplash
Why is it important?
We identify a wide set of functions that a Group Recommender System should implement, in order to, more effectively than in state of the art solutions, help groups to make decisions, which are better suited for the whole group.
Perspectives
Writing this paper was an opportunity to critically reflect on a line of research, Group Recommender Systems, that I believe can bring important and useful results, but so far has not shown its true potential.
Francesco Ricci
Read the Original
This page is a summary of: Widening the Role of Group Recommender Systems with CAJO, ACM SIGIR Forum, June 2025, ACM (Association for Computing Machinery),
DOI: 10.1145/3769733.3769745.
You can read the full text:
Contributors
The following have contributed to this page
