Explicit song lyrics detection with subword-enriched word embeddings

作者：

Highlights：

• Empirical assessment of the effectiveness of the fastText classifier and word representations for explicit lyrics detection.

• Empirical assessment of the positive impact of sub-word information of fastText embeddings in classifying explicit lyrics.

• Development of the largest (up-to-date) song lyrics dataset annotated with explicit content information.

摘要

•Empirical assessment of the effectiveness of the fastText classifier and word representations for explicit lyrics detection.•Empirical assessment of the positive impact of sub-word information of fastText embeddings in classifying explicit lyrics.•Development of the largest (up-to-date) song lyrics dataset annotated with explicit content information.

论文关键词：Word embeddings,Text classification,Explicit content detection

论文评审过程：Received 30 April 2020, Revised 30 June 2020, Accepted 11 July 2020, Available online 28 July 2020, Version of Record 6 August 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.113749