Against Filter Bubbles: Diversified Music Recommendation via Weighted Hypergraph Embedding Learning

TL;DR

The experimental results validate DWHRec as a solution that adeptly harmonizes accuracy and diversity, delivering a more enriched musical experience and can be extended to cater to other scenarios with similar data structures.

Abstract

Recommender systems serve a dual purpose for users: sifting out inappropriate or mismatched information while accurately identifying items that align with their preferences. Numerous recommendation algorithms are designed to provide users with a personalized array of information tailored to their preferences. Nevertheless, excessive personalization can confine users within a "filter bubble". Consequently, achieving the right balance between accuracy and diversity in recommendations is a pressing concern. To address this challenge, exemplified by music recommendation, we introduce the Diversified Weighted Hypergraph music Recommendation algorithm (DWHRec). In the DWHRec algorithm, the initial connections between users and listened tracks are represented by a weighted hypergraph. Simultaneously, associations between artists, albums and tags with tracks are also appended to the hypergraph. To explore users' latent preferences, a hypergraph-based random walk embedding method is applied to the constructed hypergraph. In our investigation, accuracy is gauged by the alignment between the user and the track, whereas the array of recommended track types measures diversity. We rigorously compared DWHRec against seven state-of-the-art recommendation algorithms using two real-world music datasets. The experimental results validate DWHRec as a solution that adeptly harmonizes accuracy and diversity, delivering a more enriched musical experience. Beyond music recommendation, DWHRec can be extended to cater to other scenarios with similar data structures.

Figures (7)

• Figure 1: The framework of the DWHRec algorithm. We first construct a hypergraph using the user's historical interactions and external knowledge, such as tags, albums and artists. Subsequently, a random-walks-based embedding method is employed to learn dense vector representations for users and items, facilitating top-$n$ recommendations.
• Figure 2: Summary of comparison results of our model with different baselines on evaluation metrics.
• Figure 3: Sensitivity of hyper-parameter $k$. $k$ denotes the number of steps a vertex taken in each iteration of random walk.
• Figure 4: Sensitivity of hyper-parameter $r$. $r$ controls the number of iterations for random walk on vertices.
• Figure 5: Sensitivity of hyper-parameter $s$. $s$ adjusts the dimension of the vector representation for vertices.