📖 ABSTRACT/OVERVIEW
This research applies computational musicology and machine learning methodologies to analyse genre evolution and lyrical sentiment trends in Nigerian popular music between 2010 and 2024. The rapid diversification of Nigerian popular music, encompassing Afrobeats, Afropop, Alté, Amapiano-influenced sounds, and various regional hybrids, presents a richly complex dataset ideal for computational analysis. This study constructs a corpus of 2,000 Nigerian popular music recordings drawn systematically across years, genres, and regions, extracting audio features using librosa and Essentia libraries and lyrics from licensed data sources for sentiment and thematic analysis. Supervised machine learning classifiers, including support vector machines and convolutional neural networks, are trained on annotated genre labels. Unsupervised clustering methods reveal emergent sonic typologies. Natural language processing techniques are applied to lyrical data, examining sentiment trajectories, topic modelling outputs, and linguistic diversity indices across the 14-year period. Time-series analysis tracks feature evolution at genre and artist levels. The study engages critically with the limitations of computational methods applied to culturally specific non-Western music corpora and proposes corrective frameworks for bias reduction. Findings will produce the first large-scale computational portrait of Nigerian popular music evolution and contribute methodological innovations to African popular music studies at the intersection of humanities and data science. Keywords: Computational musicology, machine learning, Nigerian popular music, genre evolution, lyrical sentiment.
Need Complete Chapters of the Above Topic?
Get high-quality, Zero-AI research materials with current citations.
Request via WhatsApp 💬