Using Natural Language Processing to Analyse the Musical Lyric Decency of Malaysia’s Top Hit Songs

This project focuses on detecting sensitive content within song lyrics of Malaysia’s top rated songs by implementing Natural Language Processing (NLP). This project requires the research and development in both “Explicit Content” exploration and analysis as well as “Sentiment Analysis” in both the Malay and English language. Malaysians love listening to music in multiple languages however this project intends to focus only on the English and Malay languages. As of currently, there are no publicly available datasets that can be used for the project which means that a dataset has that meets the requirements of the project needs to be created beforehand.