Understanding Latent Factors Using a GWAP

Kunkel, J., Loepp, B., & Ziegler, J. (2018). Proceedings of the Late-Breaking Results Track Part of the Twelfth ACM Conference on Recommender Systems (RecSys ’18).


Recommender systems relying on latent factor models often appear as black boxes to their users. Semantic descriptions for the factors might help to mitigate this problem. Achieving this automatically is, however, a non-straightforward task due to the models’ statistical nature. We present an output-agreement game that represents factors by means of sample items and motivates players to create such descriptions. A user study shows that the collected output actually reflects real-world characteristics of the factors.


Related publications

User-centered recommender systems

More »

Research development

Games with a Purpose for Understanding Latent Factors

Game that helps understanding latent factor models used in recommender systems

Focus area