Skip to content

This research study employs a mixed-methods approach to analyze the global growth of Nigerian music, utilizing data from Spotify, UK Charts, and the Billboard Hot 100. Various data analysis techniques like descriptive statistics and sentiment analysis are applied, alongside predictive models like 1D CNN and Decision Trees.

Notifications You must be signed in to change notification settings

Harbim001/Analysing_Nigerian_Music_Growth_Globally

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 

Repository files navigation

Research on the Global Impact of Nigerian Music

Table of Contents

  1. Methodology
  2. Presentation of Collected Data
  3. Sentiment Analysis
  4. Predictive Models
  5. Conclusion

Methodology

Research Design and Approach

The study adopts a mixed-methods approach combining both quantitative and qualitative methods to understand the global growth of Nigerian music.

Data Collection Methods and Sources

Methods include Spotify API for streaming data, Official UK Charts and Billboard Hot 100 for chart data, sentiment analysis via Twitter, and document analysis.

Sampling and Selection Criteria

The study targets Nigerian artists with international recognition on platforms like Spotify, Official UK Charts, and the Billboard Hot 100.

Data Analysis Techniques

Quantitative data will be analyzed through descriptive and inferential statistics. Qualitative data will be subject to thematic analysis.


Presentation of Collected Data

Spotify Data

Analyzed streaming numbers of selected Nigerian artists from 2018-2022 to compare their popularity over the years.

Official UK Charts

Data from the UK charts was analyzed to see how Nigerian artists like Burna Boy, Wizkid, and Rema have been performing in international markets.

Billboard Hot 100

Data from the Billboard Hot 100 was also examined, focusing on artists like Tems, CKay, and Burna Boy.


Sentiment Analysis

Twitter data reveals a generally positive sentiment towards Nigerian music, with 60.2% positive tweets.


Predictive Models

1D CNN for Genre Classification

A 1D CNN model achieved a test accuracy of 0.79 in classifying tracks as Afrobeats or Non-Afrobeats.

Decision Tree Model

A Decision Tree model classified tracks based on audio features, with an accuracy of 0.77.


Conclusion

Both the quantitative and qualitative data collected showcase the global impact and growth of Nigerian music. The predictive models can be valuable tools for future studies and industry applications.


To view the full research, please refer to the complete study documentation

About

This research study employs a mixed-methods approach to analyze the global growth of Nigerian music, utilizing data from Spotify, UK Charts, and the Billboard Hot 100. Various data analysis techniques like descriptive statistics and sentiment analysis are applied, alongside predictive models like 1D CNN and Decision Trees.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages