The files within this repository were utilized for an analysis of the HOT 100 songs from Billboard. Using Python for sentiment analysis, network analysis, and topic modeling on lyrics and genres, our goal was to deepen our understanding of the prevailing themes and emotions in music.

The final report is available at the following link: Mapping the Billboard Song Trends: Analyzing Lyrics and Genres across Time

In this collaborative project, specific responsibilities were assigned to ensure a comprehensive analysis shown as below:

• Data Collection: Ruishi Yang
• RQ1: Yi (Evangeline) Chang
• RQ2: Ying Yang, Yitong Ouyang
• RQ3: Ruishi Yang
• RQ4: Yitong Ouyang
• RQ5: Yingtong Peng

What is the sentiment of lyrics by genre? Is there a trend through the past 20 years?

How has the use of positive and negative words in lyrics evolved across different music genres during the selected two periods?

What topics do the lyrics mainly present?

Did the technology, society, or the public affect the change of sentiment or genres?

What’s the similarity between the genres? How is it changing through the 20 years?

• Wikipedia - Billboard Year-End Hot 100 Chart: Title, Artist, Year
• Music Genre Finder: Genre, Sub-Genre
• Musixmatch: Lyrics
• Last.fm API: Song Lengths