It's been a long time since I watched the The Simpsons , but I was always under the impression that Bart was the primary character. Perhaps it was all the Do the Bartman and "Cowabunga!" nonsense from the 90s. Anyway, data scientist Todd W Schneider used R to analyze the scripts of the first 26 seasons and found that Homer speaks twice as much as next most represented character, Marge. Bart comes a close third.
您需要 登录 才可以下载或查看，没有帐号？立即注册
Homer, not Bart, is the star of the Simpsons
Marge and Lisa are represented in orange (the color of Lisa's dress, in fact) as the only 2 female characters that make the top 10. Female representation isn't much better in the supporting cast either; only 7 characters of the top 60 (12%) are female.
Todd's R code behind the blog post is available on Github (in the analysis folder). Of note to R programmers: Todd used the gggplot2 package to create the charts and created a custom ggplot2 theme for the charts ( theme_tws_simpsons ) using the Simpsons skin yellow and the Akbar font .
For more data analysis of the Simpsons, including a look at the ratings over the last 27 years, check out the Todd's blog bost linked below.
Todd W. Schneider: The Simpsons by the Data ( via Jenny Bryan)