Episodes Discovery Recommendation with Multi-Source Augmentations

TL;DR

This paper introduces MSACL, a contrastive learning framework that enhances episode embeddings by leveraging multi-source correlated semantics, improving podcast recommendation especially for cold-start and long-tail episodes.

Contribution

It proposes a novel multi-source augmentation method within a contrastive learning framework to improve episode discovery in recommender systems.

Findings

MSACL outperforms baseline models in cold-start episode recommendation.

The framework effectively utilizes correlated semantics for better embedding learning.

Experiments show significant improvements in user engagement metrics.

Abstract

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.