Tag-Enhanced Collaborative Filtering for Increasing Transparency and Interactive Control

Donkers, T., Loepp, B., & Ziegler, J. (2016). In Proceedings of the 24th Conference on User Modeling Adaptation and Personalization (UMAP ’16) (pp. 169–173). New York, NY, USA: ACM.


To increase transparency and interactive control in Recommender Systems, we extended the Matrix Factorization technique widely used in Collaborative Filtering by learning an integrated model of user-generated tags and latent factors derived from user ratings. Our approach enables users to manipulate their preference profile expressed implicitly in the (intransparent) factor space through explicitly presented tags. Furthermore, it seems helpful in cold-start situations since user preferences can be elicited via meaningful tags instead of ratings. We evaluate this approach and present a user study that to our knowledge is the most extensive empirical study of tag-enhanced recommending to date. Among other findings, we obtained promising results in terms of recommendation quality and perceived transparency, as well as regarding user experience, which we analyzed by Structural Equation Modeling.


Related publications

Merging Latent Factors and Tags to Increase Interactive Control of Recommendations

Towards Understanding Latent Factors and User Profiles by Enhancing Matrix Factorization with Tags

Recommending Running Routes: Framework and Demonstrator


Research development


Tag-enhanced Matrix Factorization for increasing transparency and interactive control

Focus area