| Administratively Terminated Award | |
| NSF Org: |
CNS Division Of Computer and Network Systems |
| Recipient: |
|
| Initial Amendment Date: | April 19, 2022 |
| Latest Amendment Date: | May 16, 2025 |
| Award Number: | 2210137 |
| Award Instrument: | Standard Grant |
| Program Manager: |
Selcuk Uluagac
suluagac@nsf.gov (703)292-4540 CNS Division Of Computer and Network Systems CSE Directorate for Computer and Information Science and Engineering |
| Start Date: | June 1, 2022 |
| End Date: | April 25, 2025 (Estimated) |
| Total Intended Award Amount: | $300,000.00 |
| Total Awarded Amount to Date: | $300,000.00 |
| Funds Obligated to Date: |
|
| History of Investigator: |
|
| Recipient Sponsored Research Office: |
660 S MILL AVENUE STE 204 TEMPE AZ US 85281-3670 (480)965-5479 |
| Sponsor Congressional District: |
|
| Primary Place of Performance: |
ORSPA TEMPE AZ US 85281-6011 |
| Primary Place of
Performance Congressional District: |
|
| Unique Entity Identifier (UEI): |
|
| Parent UEI: |
|
| NSF Program(s): | Secure &Trustworthy Cyberspace |
| Primary Program Source: |
|
| Program Reference Code(s): |
|
| Program Element Code(s): |
|
| Award Agency Code: | 4900 |
| Fund Agency Code: | 4900 |
| Assistance Listing Number(s): | 47.070, 47.075 |
ABSTRACT
This project explores the diffusion of racial disinformation online and its social impacts, particularly focusing on Asian Americans. While the hatred and bias against Asian Americans have become notable amid the COVID-19 pandemic, Asian-targeting disinformation has yet been fully explored. The project's novelties are in unique multidisciplinary approaches to (1) detect Asian-targeting disinformation and its countermeasure messages, and understand how they are spread on the web, (2) examine how the spread of disinformation and countermeasure messages on the web is associated with the intensity of the bias and hate crimes against Asian Americans, and (3) develop various data-driven computational models to help understanding the disinformation dynamics. The project's broader significance and importance are to inform civil society, including advocacy organizations and the general public, about how to strategize communication efforts in battling racial disinformation, and to make the developed tools and outcomes publicly available for broader uses.
The project takes three-staged approaches. The main objective of the first phase is to develop computational tools for the detection and analysis of the temporal dynamics between Asian-targeted disinformation and countermeasures on the Web. A specific focus is on developing automated identification tools and deep-learning classification models by feature-engineering unique characteristics of disinformation. The objective of the second phase is to understand to what extent the spread of disinformation and countermeasures online is associated with the societal trend of implicit bias and hate crime occurrences against Asian Americans in the real-world, which can be achieved via developing deep-learning causality models. The objective of the third phase is to design scalable data-driven deep-learning models of disinformation dynamics in macro and micro levels, identifying unknown dynamics from the real-world measurements, which also enables simulations of the learned dynamics.
This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
PUBLICATIONS PRODUCED AS A RESULT OF THIS RESEARCH
Note:
When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external
site maintained by the publisher. Some full text articles may not yet be available without a
charge during the embargo (administrative interval).
Some links on this page may take you to non-federal websites. Their policies may differ from
this site.
PROJECT OUTCOMES REPORT
Disclaimer
This Project Outcomes Report for the General Public is displayed verbatim as submitted by the Principal Investigator (PI) for this award. Any opinions, findings, and conclusions or recommendations expressed in this Report are those of the PI and do not necessarily reflect the views of the National Science Foundation; NSF has not approved or endorsed its content.
This project studied (dis)information on “Asian American” on the Web and developed fundamental machine learning tools to analyze such data (that is, the data which exhibit dynamical nature over time, disproportion over different groups, and complex graph structure).
The tangible outcomes of this project include three papers published in top-tier CS conferences, one technical manuscript, and development of new course materials.
Three published papers in top-tier conferences venues:
[1] “Not All Asians are the Same: A Disaggregated Approach to Identifying Anti-Asian Racism in Social Media”, F Wu, S Lakhanpal, Q Li, K Lee, D Kim, H Chae, K H Kwon, in Proceedings of the ACM on Web Conference 2024 (theWebConf 2024).
[2] “Identifying Contemporaneous and Lagged Dependence Structures by Promoting Sparsity in Continuous-time Neural Networks”, F Wu, W Cho, D Korotky, S Hong, D Rim, N Park, K Lee, in Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, 2024 (CIKM 2024).
[3] “Reversible and irreversible bracket-based dynamics for deep graph neural networks”, A Gruber, K Lee, N Trask, in Advances in Neural Information Processing Systems 2023 (NeurIPS 2023).
One technical manuscript (which is under review on a peer-reviewed conference):
[4] “Disaggregated Health Data in LLMs: Evaluating Data Equity in the Context of Asian American Representation”, U Mudiyanselage, B Jayprakash, K Lee, K H Kwon.
In [1], the PI and the team investigated a need for disaggregated data analysis approach when it comes to perform computational studies on “Asian American” in social media; as there are diverse subgroups under the “Asian American” group, to accurately capture diversity that arise in cultural, social economical differences in each subgroup, disaggregated way of analyzing data is recommend. In [4], this study has been further extended to see if such disaggregated data practice has been used in large language models. We chose to retrieve medical information that are relevant to subgroups of “Asian American” and conducted analysis based on statistics and machine learning tools to see if the data disaggregation practice has been properly applied in generating responses.
In [2,3], the team developed fundamental tools that can be widely applicable to (1) causality discovery in time-series datasets and (2) extracting salient features from graph structured data, which is commonly seen in social media.
These findings have been disseminated through the conference venues and the team has actively participated and engaged with audiences in the conference venues. Our findings have been noticed by other groups of researchers and started get recognized and mentioned in other research papers. As the outcomes disseminate over time, we expect to see the findings have higher broader impact, influencing people outside the academic, such as Asian activist groups.
Two papers have been published in journals:
[5] "Disinformation Spillover: Uncovering the Ripple Effect of Bot-Assisted Fake Social Engagement on Public Attention". MIS Quarterly, Lee, S., Shin, D., Kwon, K. H., Han, S. P., & Lee, S. K.
[6] "Credible, but Not for Me: Immigrant Folk Theories of News Trust in Chinese, Korean, and Filipino Communities in the US". Journalism Practice, Kwon, H., Vera-Phillips, K., Moon, Y. E., Shao, C., & Xu, W. W.
Integration to the class materials: Some parts of the findings from the research activities have been incorporated into the PI’s teaching curricula and have been utilized in developing topics of students' course projects (for example, debiasing an image dataset to remove ethnic stereotypes).
Mentoring: The intangible outcomes include the increased knowledge and skills of the PIs and the PhD students who got involved, building stronger relationships between the PI and the co-PIs, and expanding a network through the conference participations. In particular, the PhD student of the PI had experienced the first and the second publication and the conference participation experience through the support of this award, making a presence to the research community and growing up as a responsible member of it. A master student of the PI who participated in the project had graduated with a master’s thesis under the topic that is relevant to this project and partially supported financially under this grant. The student gained a significant amount of deep learning development experiences and has landed on a start-up company.
Last Modified: 01/31/2025
Modified by: Kookjin Lee
Please report errors in award information by writing to: awardsearch@nsf.gov.
