Episodes Discovery Recommendation with Multi-Source Augmentations
This work addresses the challenge of recommending cold-start items in podcast platforms, which is an incremental improvement over existing methods.
The paper tackles the problem of sparse historical interaction data and long-tail items in recommender systems, particularly for discovering novel or cold-start podcast episodes, by introducing a Multi-Source Augmentations using Contrastive Learning framework (MSACL) that improves episode embedding learning with correlated semantics, achieving effective results on a real-world podcast dataset.
Recommender systems (RS) commonly retrieve potential candidate items for users from a massive number of items by modeling user interests based on historical interactions. However, historical interaction data is highly sparse, and most items are long-tail items, which limits the representation learning for item discovery. This problem is further augmented by the discovery of novel or cold-start items. For example, after a user displays interest in bitcoin financial investment shows in the podcast space, a recommender system may want to suggest, e.g., a newly released blockchain episode from a more technical show. Episode correlations help the discovery, especially when interaction data of episodes is limited. Accordingly, we build upon the classical Two-Tower model and introduce the novel Multi-Source Augmentations using a Contrastive Learning framework (MSACL) to enhance episode embedding learning by incorporating positive episodes from numerous correlated semantics. Extensive experiments on a real-world podcast recommendation dataset from a large audio streaming platform demonstrate the effectiveness of the proposed framework for user podcast exploration and cold-start episode recommendation.