| NSF Org: |
SMA SBE Office of Multidisciplinary Activities |
| Recipient: |
|
| Initial Amendment Date: | September 5, 2018 |
| Latest Amendment Date: | September 5, 2018 |
| Award Number: | 1831848 |
| Award Instrument: | Standard Grant |
| Program Manager: |
Sara Kiesler
skiesler@nsf.gov (703)292-8643 SMA SBE Office of Multidisciplinary Activities SBE Directorate for Social, Behavioral and Economic Sciences |
| Start Date: | September 15, 2018 |
| End Date: | August 31, 2022 (Estimated) |
| Total Intended Award Amount: | $944,182.00 |
| Total Awarded Amount to Date: | $944,182.00 |
| Funds Obligated to Date: |
|
| History of Investigator: |
|
| Recipient Sponsored Research Office: |
10889 WILSHIRE BLVD STE 700 LOS ANGELES CA US 90024-4200 (310)794-0102 |
| Sponsor Congressional District: |
|
| Primary Place of Performance: |
Rolfe Hall Los Angeles CA US 90095-1484 |
| Primary Place of
Performance Congressional District: |
|
| Unique Entity Identifier (UEI): |
|
| Parent UEI: |
|
| NSF Program(s): |
Secure &Trustworthy Cyberspace, Data Infrastructure |
| Primary Program Source: |
|
| Program Reference Code(s): |
|
| Program Element Code(s): |
|
| Award Agency Code: | 4900 |
| Fund Agency Code: | 4900 |
| Assistance Listing Number(s): | 47.075 |
ABSTRACT
This project will develop an integrated research framework for sociotechnical cybersecurity research and broader investigations of information provenance by behavioral, information, and computer scientists. Currently, researchers are mainly limited to natural language processing of large bodies of online text. This project will make it possible to analyze larger information worlds, including those from such countries as China, and the flow of information, including video and audio information, in newspapers, TV, and online sources. The project addresses a core goal of cybersecurity research, which is to understand the provenance, flow, and termination of information warfare, and censorship.
The project is aimed at constructing an integrated and unified information database that combines mass communication data from TV and print sources from six locations, with data from two popular online communication platforms. The project will generate a variety of metadata and time series data on topics, actors, events, and sentiments presented in communications by automated multimodal content analysis using text, image, video, and audio. Variables will be linked to identify trajectories of information flow between communication channels through multiple platforms. It will develop a new class of computational models and algorithms that can automatically analyze both verbal and nonverbal communications data by machine learning, computer vision, deep learning, and natural language processing. This project will allow researchers across the computational and social sciences to access the metadata and time series data through a search interface for qualitative research, a statistical package for quantitative research, and various visualization tools. This project will therefore link previously untapped data sources using cutting-edge computational methods to enable scholars to conduct systematic research on large-scale patterns in the emerging information and communication ecosystem.
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.
Large scale datasets and computational analytic tools have been the key drivers in computational social science, but existing resources have mainly focused on text-based single data sources. The main goal of the project was to construct an integrated multi-platform international news database that combines both traditional mass media and social media data and to develop computational methods that can systematically track real-world events and analyze complex human and media behaviors by automated multimodal machine learning approaches.
Throughout this project, the interdisciplinary project team have created numerous multimodal media datasets that can be and used for various research topics in communication, political science, and computer science. These datasets were sourced from multiple countries and diverse platforms. Individual content items were interlinked by machine learning methods to study inter-media news flows. These resources have enabled many concrete studies utilizing multiple media sources, such as Covid-related information flow between China and the world and global protest event analysis.
The project team have also developed advanced machine learning tools and made them publicly available to researchers and students. These tools allow them to automatically analyze an enormous amount of multimodal data and tackle large scale research questions. In particular, many of these tools have improved hidden biases in AI models, which is imperative to obtain objective measures for social inquiries.
Overall, the project has led to more than 20 publications in top academic venues. This project supported more than 10 graduate students, 2 postdoctoral researchers (both are currently tenure-track assistant professors), and more than 50 undergraduate students, who made significant contributions to the project. The products of this project – the datasets and tools – will continue to be maintained and improved to support the broader research community who seek to understand human behaviors in media.
Last Modified: 05/01/2023
Modified by: Jungseock Joo
Please report errors in award information by writing to: awardsearch@nsf.gov.
