Research Project Invitations from Dr. Jen Golbeck: Fake News and Narcissism Studies

Research Project Invitations from Dr. Jen Golbeck: Fake News and Narcissism Studies

From Dr. Golbeck:

"Every year I run a couple big research projects. They have large teams and anyone who volunteers commits to a minimum of 1 hour per week of work on the project (though lots of people do more work than that because the projects are fun and exciting!). All the work and organization is virtual, so no meetings are involved. Anyone who sticks with the project to to end (usually 3-9 months, depending) gets to be a co-author on the resulting papers*. This makes the projects a nice way for anyone to try out research, learn a little more about a specific methodology, and build your CV.

I'm starting up two new projects this fall and recruiting volunteers. Anyone at any level and from any department is welcome to participate. Here's a quick description of each:

1. Building a fake news corpus - This project is designed to help people studying and building classifiers for fake news. We're shooting for something that will help with the most obvious ~25% of really fake news. The dataset will be really fake stories designed to deceive readers (e.g. "Pope Endorses Trump for President") and satirical news / entertainment fake news (The Onion, Weekly World News, etc). We will be collecting stories, saving copies of them so researchers have access, and eventually doing a characterization study (describing what these types of articles look like). After we have the dataset built, we may do some machine learning work, but I suspect that won't happen until the spring. No technical skills are required for this project.

2. Narcissism study - This is a two-part project. First will be a replication study of the Single Item Narcissism Scale described in this PLOS one paper

http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0103469

The goal will be to replicate their methods with UMD students and on mturk, and then publish the replication study (hopefully at PLOS One). No technical skills are required for this part of the project.

The second part will be to do some AI/algorithmic work on inferring someone's level of narcissism from their social media. We will ask subjects to voluntarily supply their Twitter handles in the first part of the study, and that will augment data I've been collecting for over a year with over 3,600 participants who have done the same.  This will involve some computational linguistics, network analysis, and machine learning. You should have some basic experience with those concepts if you want to join in this part of the research. And you should definitely participate in the replication study if you plan to go on to help with the AI part.

To participate in this project study, you will have to be added to my IRB protocol (for new people: this gives us approval to work with human research subjects). This means you will need to complete CITI training. It's ok if you don't have that finished now, but you'll have to complete it in the next couple weeks as we get going with the project.  You can find details on that here, but keep in mind it's not a short process - it takes hours to complete so be sure you know what you're getting into! https://www.umresearch.umd.edu/RCO/New/IRBTraining.html

If you'd like to volunteer, please fill out a form with your contact info:

Fake News form: https://goo.gl/forms/LaaJlDxrDDlFgIN93

Narcissism project form : https://goo.gl/forms/iMRGr8WWbnBH1rXB3

Next week, I'll send out messages to everyone who signed up for the projects with more details to get us started. Also, feel free to share with anyone who might be interested; the only restriction is that the Narcissism Study is restricted to UMD students/faculty because of the IRB requirements.

*For example, this one that we published at the Web Science conference this summer:

Jennifer Golbeck, Zahra Ashktorab, Rashad O. Banjo, Alexandra Berlinger, Siddharth Bhagwan, Cody Buntain, Paul Cheakalos, Alicia A. Geller, Quint Gergory, Rajesh Kumar Gnanasekaran, Raja Rajan Gunasekaran, Kelly M. Hoffman, Jenny Hottle, Vichita Jienjitlert, Shivika Khare, Ryan Lau, Marianna J. Martindale, Shalmali Naik, Heather L. Nixon, Piyush Ramachandran, Kristine M. Rogers, Lisa Rogers, Meghna Sardana Sarin, Gaurav Shahane, Jayanee Thanki, Priyanka Vengataraman, Zijian Wan, and Derek Michael Wu. 2017. A Large Labeled Corpus for Online Harassment Research. In Proceedings of the 2017 ACM on Web Science Conference (WebSci '17). ACM, New York, NY, USA, 229-233. DOI: https://doi.org/10.1145/3091478.3091509"