Less Can Be More: Exploring Population Rating Dispositions with Partitioned Models in Recommender Systems
This work addresses the challenge of optimizing recommender systems for users with varying rating behaviors, though it is incremental as it builds on existing methods like KNN CF and SVD.
The study tackled the problem of improving recommender system performance by partitioning users based on their rating dispositions, such as the percentage of negative ratings and use of the rating scale, and found that this approach enhances computational efficiency, top-k performance, and predictive accuracy, with the largest effects observed in user-based KNN CF.
In this study, we partition users by rating disposition - looking first at their percentage of negative ratings, and then at the general use of the rating scale. We hypothesize that users with different rating dispositions may use the recommender system differently and therefore the agreement with their past ratings may be less predictive of the future agreement. We use data from a large movie rating website to explore whether users should be grouped by disposition, focusing on identifying their various rating distributions that may hurt recommender effectiveness. We find that such partitioning not only improves computational efficiency but also improves top-k performance and predictive accuracy. Though such effects are largest for the user-based KNN CF, smaller for item-based KNN CF, and smallest for latent factor algorithms such as SVD.