Temporal and Regional Variation in Rap Lyrics

C. Johnson-Roberson and M. Johnson-Roberson

Workshop Paper, NeurIPS '13 Workshop on Topic Models: Computation, Application and Evaluation, December, 2013

Abstract

Probabilistic topic models offer a way to explore rap lyrics across space and time, on a larger scale than is possible in traditional content analysis. By applying latent Dirichlet allocation (LDA) and Dirichlet-multinomial regression (DMR) to a corpus of transcribed rap lyrics, we uncover expected topics such as street life, drugs, and violence, but also less obvious ones such as “family/childhood reminiscence” which have not been adequately addressed in the literature. We incorporate time and location metadata into the model, both to improve model quality and to display the temporal and regional distributions of these themes. This work challenges the narrative of a unilateral shift from an abstract “ghetto” to a concrete “hood” in rappers’ conceptions of place.

BibTeX

@workshop{Johnson-Roberson-2013-130197,
author = {C. Johnson-Roberson and M. Johnson-Roberson},
title = {Temporal and Regional Variation in Rap Lyrics},
booktitle = {Proceedings of NeurIPS '13 Workshop on Topic Models: Computation, Application and Evaluation},
year = {2013},
month = {December},
}

Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.