On User Awareness in Model-Based Collaborative Filtering Systems

Loepp, B. and Ziegler, J. (2017). Proceedings of the 1st Workshop on Awareness Interfaces and Interactions.


In this paper, we discuss several aspects that users are typically not fully aware of when using model-based Collaborative Filtering systems. For instance, the methods prevalently used in conventional recommenders infer abstract models that are opaque to users, making it difficult to understand the learned profile, and consequently, why certain items are recommended. Further, users are not able to keep an overview of the item space, and thus the alternatives that in principle could also be suggested. By summarizing our experiences on exploiting latent factor models for increasing control and transparency, we show that the respective techniques may also contribute to make users more aware of their preferences’ representation, the rationale behind the results, and further items of potential interest.

Related focus areas


Related publications

Sequential User-based Recurrent Neural Network Recommendations

Donkers, T., Loepp, B., and Ziegler, J. (2017). Proceedings of the Eleventh ACM Conference on Recommender Systems, 152–160. New York: ACM.

Interactive Recommending: Framework, State of Research and Future Challenges

Loepp, B., Barbu, C.-M., and Ziegler, J. (2016). Proceedings of the Workshop on Engineering Computer-Human Interaction in Recommender Systems, 1705, 3–13.

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.