Abstract
Recommendation systems often neglect global patterns that can be provided by clusters of similar items or even additional information such as text. Therefore, we study the impact of integrating clustering embeddings, review embeddings, and their combinations with embeddings obtained by a recommender system. Our work assesses the performance of this approach across various state-of-the-art recommender system algorithms. Our study highlights the improvement of recommendation performance through clustering, particularly evident when combined with review embeddings, and the enhanced performance of neural methods when incorporating review embeddings.
Andreas Stephan
PhD student in Natural Language Processing
My research interests include weak supervision, multi-modality and in general the integration of multiple (noisy) sources of information.