Sentiment Analysis of Biblical Stories
Here’s a bible-geeking out story for you. OpenBible.info has done a “sentiment analysis” of the Biblical record and posted an interesting graph about it (h/t O’Reilly). Here’s their methodology for you academic types:
Sentiment analysis involves algorithmically determining if a piece of text is positive (“I like cheese”) or negative (“I hate cheese”). Think of it as Kurt Vonnegut’s story shapes backed by quantitative data.
I ran the Viralheat Sentiment API over several Bible translations to produce a composite sentiment average for each verse. Strictly speaking, the Viralheat API only returns a probability that the given text is positive or negative, not the intensity of the sentiment. For this purpose, however, probability works as a decent proxy for intensity.
The visualization takes a moving average of the data to provide a coherent story.
It’s an interesting project and makes me wonder about a few things:
- The Lectionary would benefit from a sentiment analysis. I would suspect the lectionary would be heavier on the happy sentiments than the darker sentiments (it’s Good News, right? Especially when we self-select out the difficult passages). I wonder then if we are giving a full understanding of the Scripture by excluding the “bogus” chapters.
- A church’s history would benefit from a sentiment analysis. If a proper history or amalgamation of a church’s writings or committee reports (I know, a huge project), then it could be helpful for a church to understand its history and why certain periods of time seem better than others.