-
Notifications
You must be signed in to change notification settings - Fork 5
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Ducks: The Diary - completed #42
Comments
I changed the type of the project because Twitter was doing rate-limiting thingies. Now I'm using a fixed corpus, which is the Russian troll tweet database available at http://nodeassets.nbcnews.com/russian-twitter-trolls/tweets.csv, and using markovify to do the hard work of Markov chaining for me. The repo is at https://github.com/duck-master/NaNoGenMo2019. Here's a sample from the beginning:
|
Hi! I'm new to GitHub, but I've been coding for some time. (Also, possibly the youngest participant here, but I can't say for sure as I don't know about the ages of everyone else.)
As I've been thinking about this for quite some time already, I've decided to follow this idea that incorporates my favorite animal, which (as you may have guessed) is the duck. It will involve scraping some Tweets containing the word "duck", Markov chain-ing the dataset into oblivion, and formatting the result as a diary.
(My other idea was to use machine learning and a handful of other tricks to improve the interestingness and decrease the repetitiveness of dariusk/NaNoGenMo#2. However, neural nets are apparently really difficult to work with, so I'm putting this on hold.)
The text was updated successfully, but these errors were encountered: