BACKGROUND
The pervasiveness of drug culture has become evident in popular music and social media. Previous research has examined drug abuse content in both social media and popular music; however, to our knowledge, the intersection of drug abuse content in these two domains has not been explored. To address the ongoing drug epidemic, we conducted an analysis of drug abuse content on Twitter, with a specific focus on lyrics. Our study provides a unique perspective on the prevalence of drug abuse in the United States.
OBJECTIVE
Our objective is to investigate of drug trends in popular music and the audience’s reaction to them by analyzing Twitter posts from 2015 through 2017. We aim to create a prediction model for future drug epidemics and to gain a deeper understanding of the characteristics of users who cited drug abuse lyrics on Twitter, based on the collected data.
METHODS
This study utilizes a quantitative analysis approach by collecting Twitter data from 2015 to 2017 through the Twitter streaming API. Substance and alcohol use lyrics are gathered from the Genius lyrics database using the Genius API. To identify substance and alcohol use lyrics on Twitter, we searched against the lyrics database that we collected as our reference. We employed term frequency analysis to classify the types of drugs mentioned in tweets, time series analysis to study the trends, and cross analysis with the Billboard Top-100 year-end chart to measure the popularity of the original references.
RESULTS
In our research, we processed over 1.9 billion publicly available tweets from 2015 to 2017, resulting in the identification of over 157 million tweets that matched drug-related keywords. Among them, we identified 150,746 tweets referencing substance and alcohol use lyrics, revealing a decline in the number of drug abuse lyrics over the three-year period, contradicting our initial hypothesis. Notably, cannabinoids, opioids, stimulants, and hallucinogens emerged as the most frequently mentioned drugs in lyrics. Furthermore, the majority of drug abuse lyrics on Twitter (91.98%) belonged to the Rap or Hip-Hop genres, with male artists accounting for 84.21% of the performances.
CONCLUSIONS
In this study, we focused on investigating the prevalence of the drug epidemic in the U.S from a distinct perspective. Our analysis of substance and alcohol use lyrics posted on Twitter provides novel insights that could serve as an indicator for a prediction model of the ongoing drug epidemic.