This repository contains some of the materials used to prepare my talk at the [Moral Media meeting](https://moralmedia.org/annual-meeting/) at Ohio State University in September 2018. The slides, in their HTML format, are also here and can also be accessed at [this link](https://jacob-long.com/slides/MM18-slides.html). ## What is this The project involved collecting Billboard music charts in a few genres since 1992, retrieving the lyrics for those songs, and content analyzing them. In particular, I used the [Moral Foundations Dictionary](https://moralfoundations.org/othermaterials) as well as an ad hoc political words dictionary. In addition to the conventional word count analysis, I used [distributed dictionary representations](https://link.springer.com/article/10.3758%2Fs13428-017-0875-9) (DDR) to quantify the moral and political content of the lyrics. ## Use The repository is self-sufficient insofar as you should be able to generate the slides from `Slides.Rmd` with R and interact with the processed data (stored in `charts.rds`) to explore as you wish. The variable names should be fairly self-explanatory if you know Moral Foundations Theory well enough to be interested in this project. The `.ddr` suffixes differentiate the DDR loadings from the dictionary frequencies. Look to the `Slides.Rmd` file for some example code for converting the code from the format in `charts.rds` --- which is one song-chart-week per row --- to other shapes and levels, like one genre-chart-week per row. ## Raw data There are two raw data sources that I cannot include: * The raw lyrics data, because I do not own the copyright and so cannot distribute it. * The training corpus for the DDR, due to its size. You can check out [my data scraper](https://github.com/jacob-long/Song-and-Lyric-Data-Scraper) to collect your own raw lyrics data if you'd like. You can then use the `sqlite_to_R.R` and then `raw_to_counts.R` scripts to get the raw data in the same format needed to replicate the slides with `Slides.Rmd`. The training corpus I used is available at [this link](https://drive.google.com/file/d/0B7XkCwpI5KDYNlNUTTlSS21pQmM/edit). Bear in mind it is over 1GB. To install the DDR Python module, run `python setup.py install` from the DDR directory. Run `python ddr-script.py` from this project's directory on the command line to generate the DDR loadings after you have created the `unique_songs_raw.csv` file from the `raw_to_counts.R` script. Of course, I will again say that you can skip all of this and just use the `charts.rds` file if you want the data with only the dictionary counts and DDR loadings.