propose substantive next steps for your text (then close this issue by the end of the day on Monday, February 26th)

[nicholasjhorton]

The next step for your book package is to propose a substantive analysis that utilizes some technique in text analytics to explore or extract insights.

Your audience can be people new to the book, or people who know it and love it (and can quote from it).

Your deliverable is open-ended: this could be a report, a Shiny app, or something in between.

My hope is that you dream big: we can work together to come up with something that you'll be proud to show off.

Have questions? Have ideas? Please use this issue to share those thoughts.

Finally, please comment to share your proposal (then close the issue to let me know that you are ready for my review).

[nicholasjhorton]

PS if you need an extension please let me know.

[nicholasjhorton]

@jpapagelis24 can you please share your plans for your substantive analysis when you have a chance (and by the end of the day on Monday)? Thanks in advance, Nick

[jpapagelis24]

@nicholasjhorton For my substantive analysis, I would like to look at the different narrators in the novel Frankenstein and see if they are written in different styles. This could be done by analyzing each section's sentence length, structure, and common words. I could also explore the different distributions of certain words to see if the language differs. I could create a model that would read a paragraph or line and then be able to predict which section it belongs in accurately.

This will be interesting and thought-provoking because the story is told in a framing manner, which is basically a story within a story within a story. For Frankenstein, there are three narrators: Walton, Frankenstein, and The Creature, and the breakdown of the chapters is as follows.

• Walton: Letters 1-4
• Frankenstein: Chapters 1-10
• The Creature: Chapters 11-16
• Frankenstein: Chapters 17-24.5
• Walton: Rest of Chapter 24

As you can see, the different narrative sections are framed within each other, so it would be cool to see if there is variation in how the sections are written because they are each a different character's story. I could further this analysis by utilizing LDA to compare the different topics that appear within each character's perspective. I am interested in how LDA works in a setting where there is a narrative, and many things change from scene to scene.

I think it would be really fun if I had an interactive element in a Shiny app, but at the moment, I can't think of anything substantial more than choosing words for a model or picking how many topics to use for LDA. It may be possible that a standard report would be the best way to convey this analysis.

[nicholasjhorton]

I really like how these ideas are shaping up and suspect that a relatively simple Shiny app might be a great way to allow the user to explore the text.

For next steps, can you please open two new issues on GitHub that describe this plan with some detail about how:

1. the LDA analysis would be framed? and
2. what might included in a very simple Shiny app

There's no need to do any of the work now but it would be great if you could create these two issues and close this issue (which I've reopened) by class on Tuesday.

[jpapagelis24]

@nicholasjhorton I created the two new issues.