A Data-Driven Framework for Analysing the Digital Transformation of Global Music Culture Using Deep Learning and Cultural Analytics

Abstract

Recent developments in the realm of digital music platforms along with advancements in data-driven analyses have had a drastic effect on the way music has been produced, distributed and consumed. Consequently, some new paradigms for global music culture have emerged. Despite the growing popularity of data-driven analytics in studying various transformations in the area, previous researches are limited to isolated prediction models and analyses of specific music platforms. As a result, there is currently no generalised framework that would incorporate both temporal evolution and feature-level interactions within the context of digital transformation of music culture. Hence, the purpose of this study is to develop a general framework that would enable data-driven analysis of digital transformation in global music culture. For the purpose of this experiment, a dataset Spotify Global Music Dataset was used. This experiment uses a hybrid approach that involves Bidirectional Long Short-Term Memory and Deep Neural Network for temporal and feature-level learning respectively. At the same time, cultural affinity analysis based on similarity measurements was employed. The results of the experiment show that the developed model demonstrates 0.962 accuracy, 0.974 precision, 0.964 recall, 0.969 F1-Score, and 0.962 ROC-AUC respectively, thus proving its effectiveness and stability.