Author ORCID Identifier
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.
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