Analyzing and Supporting Twitter-Based Science Communication
- Spencer Williams, HCDE PhD student
- Keri Mallari, HCDE PhD student
- Gary Hsieh, HCDE faculty
- Katharina Reinecke, CSE faculty
Twitter has become an important platform for researchers to communicate about their work to the public. Much of the research done in HCI has direct applications for different groups of people, and many researchers use platforms like Twitter to disseminate their results to the people who might find it useful. However, as people’s audiences on Twitter grow larger, it becomes difficult to know who your tweets are reaching. If you tweet out a blog post with helpful knowledge for kindergarten teachers, how do you know it’s actually being seen by kindergarten teachers and not bounced around by other academics?
In this project, we will be designing a system that identifies what types of people have likely read an individual tweet (e.g., using techniques from NLP and beyond), and aggregates that information to help us summarize the current state of science communication in HCI. We hope to deploy this system on a public website, to provide researchers in our field with insights about who their tweets are reaching, and why.
Activities: In this DRG, the primary tasks will include identifying relevant HCI researchers on Twitter, using text classification to categorize Twitter users, and designing and prototyping the system and underlying algorithms. We will also be reading relevant papers about science communication on social media, NLP, and network science.
Logistics and Expectations: This will be a 2-credit DRG. We will meet for 2 hours in person each week and students will be expected to spend about 3-4 hours working outside of that time per week. Time and location will be determined based on students’ available times.
Qualifications: We are looking for students (BA, MS, PhD, or certificate) who are familiar with web development (CSE 154, HCDE 537), design (HCDE 318/418/518), and/or information visualization (HCDE 411/511, CSE 412/442/512, CS&SS 569). If interested, please email the leading PhD student Spencer Williams at firstname.lastname@example.org.