- Independent development
- Tim Donkers
- Timm Kleemann
TagMF represents an interactive recommending approach that merges user-generated tags with latent factors derived from user ratings to increase user proﬁle transparency and interactive control in Recommender Systems. Taking advantage of the Matrix Factorization technique widely used in Collaborative Filtering, the method learns an integrated model of tags and latent factors, thus enabling users to understand and manipulate their preference proﬁle expressed implicitly in the (intransparent) latent factor space through explicitly presented textual tags.
- Towards Understanding Latent Factors and User Profiles by Enhancing Matrix Factorization with Tags. Donkers, T., Loepp, B., and Ziegler, J. (2016). Poster Proceedings of the 10th ACM Conference on Recommender Systems (RecSys 2016): Boston, USA, September 17, 2016, 1688. [PDF] [BibTeX] [DuEPublico] [Web]
- Tag-Enhanced Collaborative Filtering for Increasing Transparency and Interactive Control. Donkers, T., Loepp, B., and Ziegler, J. (2016). Proceedings of the 24th Conference on User Modeling Adaptation and Personalization (UMAP ’16), 169–173. New York, NY, USA: ACM. [BibTeX] [DuEPublico] [Web]
- Merging Latent Factors and Tags to Increase Interactive Control of Recommendations. Donkers, T., Loepp, B., and Ziegler, J. (2015). Poster Proceedings of the 9th ACM Conference on Recommender Systems (RecSys 2015). [PDF] [BibTeX] [DuEPublico] [Web]