Edward Rapa III
Research Mentor(s): Christopher Fariss, Assistant Professor
Research Mentor School/College/Department: Political Science, College of Literature, Science, and the Arts
Presentation Date: Thursday, April 22, 2021
Session: Session 4 (2pm-2:50pm)
Breakout Room: Room 1
Motivation/problem statement With the growing influence that social media platforms, such as Facebook and Twitter, have on the political ideologies of an individual, our project aims to see if we can track regional political trends through these platforms too. In addition to this we are also looking at ties between climate change based migration and shifting political majorities in the counties around Houston, Texas after Hurricane Maria in 2017. The team at Christopher Fariss’s lab consists of eight urop students who are in a wide variety of schools, from computer science to art, working together in the first year of a multiyear/on going project concerning how social media plays a factor in regional political majority and the impact that climate change has on coastal communities. Methods/procedure/approach After a late start, our team collected over eight thousand individual tweets and sorted them into six categories based on subject matter. Part of our team is now using this drive of sorted tweets to train an AI bot to learn how to sort tweets itself, once up and running at full capacity this bot will greatly increase our tweet index. With each tweet we have access to a user’s metadata, meta concerns personal information such as location coordinates at time of sending, age, gender, etc. We can use this data to make inferences about where people are and what their political affiliation may be based on publicly available twitter data. In addition, our team is also creating Qualtrics surveys that ask participants specific questions about climate change and political affiliation. We hope that these surveys when combined with a participants metadata will confirm our theory that a person’s tweets are a good representation of their ideology From the collected data and survey information another section of our team is translating this information in a visual format through the use of a geographic information system or ArcGIS. We hope that this visual information will better illustrate the ties between how social media plays a factor in regional political majority and the impact that climate change has on coastal communities. Conclusion/implications Although our project is in its early stages our research team hopes to establish a foundation practice to more efficiently collect twitter and survey data, in addition to create a standard for spatial data infographics. In doing so, our goal is to allow the next three to four years of the project to use our framework to better understand the ties between climate change based migration and shifting political majorities in regions affected by severe weather events.