Integrating methods from network analysis, natural language processing, and machine learning with theories from the social sciences to advance knowledge and discovery about interaction-based and communication-based social systems

Current Projects | Completed Projects

Current Projects:

Impact Assessment
Impact of science on society
TextTransfer
  • Assessing Impact Patterns in Research Texts Applying Corpus Driven Methods, 2020-2023
  • Corpus-based Detection of Secondary Use of Scientific Publications, 2017-2019
This collaborative project uses natural language processing and machine learning to identify secondary practical uses of research findings from final reports of grant funded work, we identify practically relevant patterns from text data and detect transferable knowledge (from basic research to applications) in selected domains...[Learn More]
Impact of funding on society
Conservation Legacies: Understanding the Long-term Impacts of Private Foundation Investment in International Biodiversity Conservation, 2019-2021
This multi-institutional project traces key outcomes of the long-term impacts of MacArthur Foundation's global conservation investments. We will focus on comparing impacts based on analyzing text documents versus grantees' interviews...[Learn More]
Impact of works of art on society
Computational impact assessment of issue focused media and information products
This project proposed a solution for measuring impact of social justice documentaries in a theoretically grounded, systematic, empirical, scalable and rigorous fashion using computational approaches and to gain novel substantive knowledge providing actionable insights for film makers and funders...[Learn More]
Crisis Informatics
Network analysis and information extraction for Humanitarian Assistance and Disaster Relief (HADR)
Reliable Extraction of Emergency Response Networks from Text Data and Bench-marking with National Emergency Response Guidelines, 2019-2020
This project employs techniques from natural language processing and social network analysis to identify and evaluate multi-modal networks involved in Humanitarian Assistance and Disaster Relief (HADR) efforts. This project contains the following 3 research components:
  • Relation extraction: evaluation of methods for extracting relational data from texts.
  • Link labeling: development of domain specific model and method for edge classification.
  • Network comparison: comparison of extracted networks to mandated interaction networks.
...[Learn More]
Machine learning and natural language processing for Humanitarian Assistance and Disaster Relief (HADR)
Review and Assessment of the Usage of Computational Methods for Humanitarian Assistance and Disaster Relief (HADR) Efforts, and Scalable Measurement of Emergency Response from Text Data, 2017-2018
The Humanitarian Assistance and Disaster Relief (HADR) project has endeavored to use natural language processing (NLP) to increase situational awareness of humanitarian relief operations. Our methods-oriented approach augments existing efforts by comparing different sources of text-based communication to an established ground truth...[Learn More]
Social Computing for Intelligence Analysis
Internet of battlefield things
Alliance for IoBT Research on Evolving Intelligent Goal-driven Networks (IoBT REIGN), 2017-2022
The IoBT REIGN is a multi-institutional initiative funded by the Army Research Lab (under W911NF-17-2-0196) to enable new predictive battlefield analytics and services. Our team focuses on the following research component:
  • Morality, stance, and images: measuring individuals’ perception from user-generated texts when they are exposed to various types of information with embedded stimuli.
Network Theory
  • Multilevel structural evaluation of signed and directed graphs, in collaboration with Max Planck Institute in Germany
  • New method and computational analysis of transitivity in balance assessment
Social Science Theory
  • Cross-cutting exposure validation on contemporary data and interactions, joint work with Cline Center for Advances Social Research and Hebrew University in Jerusalem
Adversarial Learning
  • Design and prevention of metric-based adversarial attacks on social network data
Fairness, Accountability, Transparency, Ethics
  • Gender biases in public reporting, in collaboration with Cline Center for Advances Social Research and faculty member from the business school

    Hurricanes are ungendered phenomena that are ascribed with gendered names. We examined if people, in this case authors of news articles and individuals quoted in news, use gendered language when referring to hurricanes. This work helps identify if people use gender stereotyping when referring to gender-neutral entities, and what these stereotypes might be.
Data Compliance and Governance
  • Developing organizational expertise and resources as well as publications on the responsible conduct of research with human generated and publicly available data

Thanks to our sponsors:

funder_logos