skip to main content

Attention:

The NSF Public Access Repository (NSF-PAR) system and access will be unavailable from 11:00 PM ET on Thursday, May 23 until 2:00 AM ET on Friday, May 24 due to maintenance. We apologize for the inconvenience.


Title: Reinforcement Learning-based Counter-Misinformation Response Generation: A Case Study of COVID-19 Vaccine Misinformation
Award ID(s):
2154118
NSF-PAR ID:
10500303
Author(s) / Creator(s):
; ;
Publisher / Repository:
ACM
Date Published:
Page Range / eLocation ID:
2698 to 2709
Format(s):
Medium: X
Location:
Austin TX USA
Sponsoring Org:
National Science Foundation
More Like this
  1. This paper examines strategies for making misinformation interventions responsive to four communities of color. Using qualitative focus groups with members of four non-profit organizations, we worked with community leaders to identify misinformation narratives, sources of exposure, and effective intervention strategies in the Asian American Pacific Islander (AAPI), Black, Latino, and Native American communities. Analyzing the findings from those focus groups, we identified several pathways through which misinformation prevention efforts can be more equitable and effective. Building from our findings, we propose steps practitioners, academics, and policymakers can take to better address the misinformation crisis within communities of color. We illustrate how these recommendations can be put into practice through examples from workshops co-designed with a non-profit working on disinformation and media literacy. 
    more » « less
  2. null (Ed.)
  3. As the internet and social media continue to become increasingly used for sharing break- ing news and important updates, it is with great motivation to study the behaviors of online users during crisis events. One of the biggest issues with obtaining information online is the veracity of such content. Given this vulnerability, misinformation becomes a very danger- ous and real threat when spread online. This study investigates misinformation debunking efforts and fills the research gap on cross-platform information sharing when misinforma- tion is spread during disasters. The false rumor “immigration status is checked at shelters” spread in both Hurricane Harvey and Hurricane Irma in 2017 and was analyzed in this paper based on a collection of 12,900 tweets. By studying the rumor control efforts made by thousands of accounts, we found that Twitter users respond and interact the most with tweets from verified Twitter accounts, and especially government organizations. Results on sourcing analysis show that the majority of Twitter users who utilize URLs in their post- ings are employing the information in the URLs to help debunk the false rumor. The most frequently cited information comes from news agencies when analyzing both URLs and domains. This paper provides novel insights into rumor control efforts made through social media during natural disasters and also the information sourcing and sharing behaviors that users exhibit during the debunking of false rumors. 
    more » « less