Cartoon Analysis is a blog devoted to using natural language processing tools in Python and R to analyze dialogue in cartoons, primarily children’s cartoons written in English. Findings related to word frequency, lexical diversity, sentiment analysis, and other methods are used to discover the unique characteristics about the shows, characters, and writers’ writing styles.
The blog is an ongoing process. Results are posted as tests are done, and more shows are added once a file of the transcripts is compiled. New posts will be made once a week.
Reader engagement is welcome, and even encouraged. If you have questions regarding the blog, if you are familiar with text mining methods and have any suggestions, if you are a fan of a show and would like to know something about the show I haven’t done yet, please reach out to me at the Contact Page, or comment on a post.
If you aren’t familiar with text mining/text analysis but are interested in learning, I am willing to answer any questions you have, but I would also suggest other resources such as the NLTK Book or sentdex’s YouTube tutorial on NLTK with Python 3.