Assessing Fine-Grained Explicitness of Song Lyrics

Music plays a crucial role in our lives, with growing consumption and engagement through streaming services social media platforms. However, caution is needed for children, who may be exposed to explicit content songs. Initiatives such as the Parental Advisory Label (PAL) similar labelling from providers aim protect children harmful content. so far, has been limited tagging song (if so), without providing any additional information on reasons explicitness (e.g., strong language, sexual reference). This paper addresses this issue by developing system capable of detecting lyrics assessing kind detected. The novel contributions work include (i) new dataset 4000 annotated five possible (ii) experiments machine learning classifiers predict it. results demonstrated feasibility automatically lyrics. first address at level detail provides valuable contribution music industry, helping exposure inappropriate