The purpose of this project is to analyze data from Twitter using Big Data tools to see what Lupus patients, and others affected by Lupus, are saying. This information can be used to help direct Lupus research.
Twitter has a an array of APIs available to us developers, but we mostly use the search APIs.
To run our code and use these APIs to gather data, you'll need to get your own API access tokens from the Twitter developer's page. (We keep our private access tokens off this public repo).
The two languages we use mostly are R and Python 3.x as they're friendly with data analysis, and easy languages to get started in for a project like this.
To make gathering data easier, we use packages such as rtweet and Twython.
Here are notebooks with our findings: