Author ORCID Identifier
Document Type
Article
Publication Date
5-2019
Abstract
A hybrid recommender system fuses multiple data sources, usually with static and nonadjustable weightings, to deliver recommendations. One limitation of this approach is the problem to match user preference in all situations. In this paper, we present two user-controllable hybrid recommender interfaces, which offer a set of sliders to dynamically tune the impact of different sources of relevance on the final ranking. Two user studies were performed to design and evaluate the proposed interfaces.
Recommended Citation
Rahdari, B., Tsai, C. H., & Brusilovsky, P. (2019). Expanding Controllability of Hybrid Recommender Systems: From Positive to Negative Relevance. In The Thirty-Second In- ternational Flairs Conference. https://sites.google.com/view/flairs-32homepage/home
Comments
This has been deposited with permission from AAAI press.
This was the Runner-up for Best Poster Award at the 32nd International Flairs Conference. https://sites.google.com/view/flairs-32homepage/home