Content-based feature exploration for transparent music recommendation using self-attentive genre classification

by   Seungjin Lee, et al.

Interpretation of retrieved results is an important issue in music recommender systems, particularly from a user perspective. In this study, we investigate the methods for providing interpretability of content features using self-attention. We extract lyric features with the self-attentive genre classification model trained on 140,000 tracks of lyrics. Likewise, we extract acoustic features using the acoustic model with self-attention trained on 120,000 tracks of acoustic signals. The experimental results show that the proposed methods provide the characteristics that are interpretable in terms of both lyrical and musical contents. We demonstrate this by visualizing the attention weights, and by presenting the most similar songs found using lyric or audio features.


Visualizing and Understanding Self-attention based Music Tagging

Recently, we proposed a self-attention based music tagging model. Differ...

Multimodal Fusion Based Attentive Networks for Sequential Music Recommendation

Music has the power to evoke intense emotional experiences and regulate ...

NAIRS: A Neural Attentive Interpretable Recommendation System

In this paper, we develop a neural attentive interpretable recommendatio...

Music theme recognition using CNN and self-attention

We present an efficient architecture to detect mood/themes in music trac...

Time-aware Self-Attention Meets Logic Reasoning in Recommender Systems

At the age of big data, recommender systems have shown remarkable succes...

Event-related data conditioning for acoustic event classification

Models based on diverse attention mechanisms have recently shined in tas...

Attention-based Multimodal Feature Representation Model for Micro-video Recommendation

In recommender systems, models mostly use a combination of embedding lay...