Learning Consumer and Producer Embeddings for User-Generated Content Recommendation
This addresses recommendation challenges in UGC platforms where users have dual roles, offering an incremental improvement over existing methods.
The paper tackles the problem of recommending user-generated content by modeling users as both consumers and producers, proposing CPRec which learns separate role embeddings for each user. The method outperforms standard collaborative filtering and recent producer-aware approaches on two large-scale applications.
User-Generated Content (UGC) is at the core of web applications where users can both produce and consume content. This differs from traditional e-Commerce domains where content producers and consumers are usually from two separate groups. In this work, we propose a method CPRec (consumer and producer based recommendation), for recommending content on UGC-based platforms. Specifically, we learn a core embedding for each user and two transformation matrices to project the user's core embedding into two 'role' embeddings (i.e., a producer and consumer role). We model each interaction by the ternary relation between the consumer, the consumed item, and its producer. Empirical studies on two large-scale UGC applications show that our method outperforms standard collaborative filtering methods as well as recent methods that model producer information via item features.