ORCID Identifier(s)

0000-0002-0900-7634

Graduation Semester and Year

2022

Language

English

Document Type

Thesis

Degree Name

Master of Science in Computer Science

Department

Computer Science and Engineering

First Advisor

Shirin Nilizadeh

Abstract

Social media platforms have brought people from different backgrounds, ethnicity, race, gender, etc together to form a platform to share ideas and opinions and discuss news events among other social events. Unfortunately, these platforms have also been a safe haven for abusive users who harass, bully other users or spread misinformation and disinformation. Social media platforms have a huge incentive to police these abusive users and keep them in check to allow other genuine users to use their platform. Social media platforms employ several different content moderation techniques to perform this task. These techniques vary across platforms, for example, Parler believes in using the least restrictive moderation policies and having open discussion spaces for their users. These policies were used by several members responsible for the 2021 US Capitol Riots. On January 12, 2021, Parler a social media platform popular among conservative users was removed from the Apple App store, the Google Play Store, and Amazon Web Services. This was blamed on Parler’s refusal to remove posts inciting violence following the 2021 US Capitol Riots. To return to the app stores, Parler would have to modify their moderation policies drastically. Shortly before being banned from Amazon Web Services, a Twitter user, donk_enby, published frameworks and methodology for scraping Parler using their open API service. Studies like Aliapoulios et al. used this opportunity to collect a dataset of posts from Parler and record user information. After a month of downtime, with a new cloud service provider and a new set of user guidelines, Parler was back online. Our study looks into the moderation changes performed by Parler and studies any noticeable differences in user behavior. Using Google’s Perspective API, we notice a decrease in the toxicity content shared in posts. We also notice similar trends in other labels such as identity attack, insult, severe toxicity, profanity, and threats. We study the most popular topics being talked about on Parler and compare other topics to uncover any changes in the topics of discussion. Finally, the Media Bias Fact Check service also checks the factuality of a sample of news websites being shared. We find an increase in the factuality in the news sites being shared. We also notice a decrease in the number of questionable sources and conspiracy or pseudoscience sources being shared.

Keywords

Social media, Privacy, Capitol riots, Online moderation, Perspective api, Media bias fact check, Deplatforming

Disciplines

Computer Sciences | Physical Sciences and Mathematics

Comments

Degree granted by The University of Texas at Arlington

Download

Share

COinS