Deep learning based mood tagging for Chinese song lyrics

TL;DR

This paper develops a CNN-based deep learning model with pre-trained word embeddings to accurately tag the mood of Chinese song lyrics, significantly outperforming traditional and other deep learning methods.

Contribution

It introduces an effective CNN-based approach with pre-trained embeddings for Chinese lyrics mood tagging, leveraging a large corpus for improved accuracy.

Findings

CNN with pre-trained embeddings outperforms traditional methods by 15%

Deep learning models outperform machine learning models in mood tagging

Large corpus pre-training enhances mood tagging accuracy

Abstract

Nowadays, listening music has been and will always be an indispensable part of our daily life. In recent years, sentiment analysis of music has been widely used in the information retrieval systems, personalized recommendation systems and so on. Due to the development of deep learning, this paper commits to find an effective approach for mood tagging of Chinese song lyrics. To achieve this goal, both machine-learning and deep-learning models have been studied and compared. Eventually, a CNN-based model with pre-trained word embedding has been demonstrated to effectively extract the distribution of emotional features of Chinese lyrics, with at least 15 percentage points higher than traditional machine-learning methods (i.e. TF-IDF+SVM and LIWC+SVM), and 7 percentage points higher than other deep-learning models (i.e. RNN, LSTM). In this paper, more than 160,000 lyrics corpus has been leveraged for pre-training word embedding for mood tagging boost.