Research Projects
Filtered by: Machine Learning, AI, Computational Linguistics, and Information Retrieval
III: Small: Bringing Transparency and Interpretability to Bias Mitigation Approaches in Place-based Mobility-centric Prediction Models for Decision
Principal Investigator(s): Vanessa Frias-Martinez
Funders: National Science Foundation
Research Areas: Data Science, Analytics, and Visualization Health Informatics Information Justice, Human Rights, and Technology Ethics Machine Learning, AI, Computational Linguistics, and Information Retrieval
The project focuses on improving the fairness of place-based mobility-centric (PBMC) prediction models, particularly in high-stakes scenarios like public health and safety. By addressing biases in COVID-19 mobility and case data, it aims to make predictions more accurate and equitable. The research introduces novel bias-mitigation and interpretability methods across three technical thrusts, promoting transparency in PBMC models.
Principal Investigator(s): Vanessa Frias-Martinez
Funders: National Science Foundation
Research Areas: Data Science, Analytics, and Visualization Health Informatics Information Justice, Human Rights, and Technology Ethics Machine Learning, AI, Computational Linguistics, and Information Retrieval
The project focuses on improving the fairness of place-based mobility-centric (PBMC) prediction models, particularly in high-stakes scenarios like public health and safety. By addressing biases in COVID-19 mobility and case data, it aims to make predictions more accurate and equitable. The research introduces novel bias-mitigation and interpretability methods across three technical thrusts, promoting transparency in PBMC models.
Information Technology Access RERC
Principal Investigator(s): J. Bern Jordan Amanda Lazar Hernisa Kacorri
Funders: DHHS-Administration for Community Living Other Federal
Research Areas: Accessibility and Inclusive Design Human-Computer Interaction Information Justice, Human Rights, and Technology Ethics Machine Learning, AI, Computational Linguistics, and Information Retrieval Youth Experience, Learning, and Digital Practices
The University of Maryland Information Technology RERC aims to improve accessibility for people with disabilities through research, technology development, and standards creation. Key initiatives include individualizing generative AI, enhancing usability for older adults, developing cross-disability solutions, and creating open-source tools and guidelines to ensure broad, equitable access to information and communication technologies.
Principal Investigator(s): J. Bern Jordan Amanda Lazar Hernisa Kacorri
Funders: DHHS-Administration for Community Living Other Federal
Research Areas: Accessibility and Inclusive Design Human-Computer Interaction Information Justice, Human Rights, and Technology Ethics Machine Learning, AI, Computational Linguistics, and Information Retrieval Youth Experience, Learning, and Digital Practices
The University of Maryland Information Technology RERC aims to improve accessibility for people with disabilities through research, technology development, and standards creation. Key initiatives include individualizing generative AI, enhancing usability for older adults, developing cross-disability solutions, and creating open-source tools and guidelines to ensure broad, equitable access to information and communication technologies.
Institute for Trustworthy AI in Law and Society (TRAILS)
Principal Investigator(s): Katie Shilton
Funders: National Science Foundation
Research Areas: Information Justice, Human Rights, and Technology Ethics Machine Learning, AI, Computational Linguistics, and Information Retrieval
The TRAILS (Trustworthy AI in Law and Society) Institute, a collaboration among several universities, aims to enhance trust in AI systems. It focuses on community participation, transparent design, and best practices. Four key research thrusts address social values, technical design, socio-technical perceptions, and governance. The institute seeks to include historically marginalized communities and promote informed AI adoption.
Principal Investigator(s): Katie Shilton
Funders: National Science Foundation
Research Areas: Information Justice, Human Rights, and Technology Ethics Machine Learning, AI, Computational Linguistics, and Information Retrieval
The TRAILS (Trustworthy AI in Law and Society) Institute, a collaboration among several universities, aims to enhance trust in AI systems. It focuses on community participation, transparent design, and best practices. Four key research thrusts address social values, technical design, socio-technical perceptions, and governance. The institute seeks to include historically marginalized communities and promote informed AI adoption.
Integration of Computer-Assisted Methods and Human Interactions to Understand Lesson Plan Quality and Teaching to Advance Middle-Grade Mathematics Instruction
Principal Investigator(s): Wei Ai
Funders: National Science Foundation
Research Areas: Data Science, Analytics, and Visualization Future of Work Human-Computer Interaction Machine Learning, AI, Computational Linguistics, and Information Retrieval Youth Experience, Learning, and Digital Practices
This NSF-funded project uses machine learning, human coding, and teacher input to evaluate the quality of middle-grades mathematics lesson plans. By combining computational analysis with educator perspectives, it aims to improve how instructional materials are assessed and used in classrooms.
Principal Investigator(s): Wei Ai
Funders: National Science Foundation
Research Areas: Data Science, Analytics, and Visualization Future of Work Human-Computer Interaction Machine Learning, AI, Computational Linguistics, and Information Retrieval Youth Experience, Learning, and Digital Practices
This NSF-funded project uses machine learning, human coding, and teacher input to evaluate the quality of middle-grades mathematics lesson plans. By combining computational analysis with educator perspectives, it aims to improve how instructional materials are assessed and used in classrooms.
Machine Learning Strategies for FDR Presidential Library Collections (ML-FDR)
Principal Investigator(s): Richard Marciano
Funders: Unfunded
Research Areas: Archival Science Data Science, Analytics, and Visualization Machine Learning, AI, Computational Linguistics, and Information Retrieval
Demonstrate computational treatments of digital cultural assets using Artificial Intelligence (AI) and Machine Learning (ML) techniques that can help unlock hard-to-reach archival content related to WWII-era records housed at the FDR Presidential Library. This content is under-utilized by scholars examining American responses to the Holocaust.
Principal Investigator(s): Richard Marciano
Funders: Unfunded
Research Areas: Archival Science Data Science, Analytics, and Visualization Machine Learning, AI, Computational Linguistics, and Information Retrieval
Demonstrate computational treatments of digital cultural assets using Artificial Intelligence (AI) and Machine Learning (ML) techniques that can help unlock hard-to-reach archival content related to WWII-era records housed at the FDR Presidential Library. This content is under-utilized by scholars examining American responses to the Holocaust.
Piloting Lab Discourse Graphs for Sustainable Research Communication
Principal Investigator(s): Joel Chan
Funders: The Navigation Fund; Chan Zuckerberg Initiative (CZI) Other Non-Federal
Research Areas: Data Science, Analytics, and Visualization Human-Computer Interaction Machine Learning, AI, Computational Linguistics, and Information Retrieval
This project develops tooling for Discourse Graphs, a system enabling researchers to share and build on evidence-based research. Supported by $1.35M from the Chan-Zuckerberg Initiative and Navigation Fund, it collaborates with a PI at UW to enhance research workflows and open-science practices.
Principal Investigator(s): Joel Chan
Funders: The Navigation Fund; Chan Zuckerberg Initiative (CZI) Other Non-Federal
Research Areas: Data Science, Analytics, and Visualization Human-Computer Interaction Machine Learning, AI, Computational Linguistics, and Information Retrieval
This project develops tooling for Discourse Graphs, a system enabling researchers to share and build on evidence-based research. Supported by $1.35M from the Chan-Zuckerberg Initiative and Navigation Fund, it collaborates with a PI at UW to enhance research workflows and open-science practices.
Quantum Choreobotics: Democratizing Quantum Computing Through Interactive Dance/ Theater Performance, With On-Body Robots
Principal Investigator(s): Bill Kules
Funders: UMD Funded
Research Areas: Data Science, Analytics, and Visualization Digital Humanities Health Informatics Human-Computer Interaction Machine Learning, AI, Computational Linguistics, and Information Retrieval
UMD researchers Bill Kules and Huaishu Peng are exploring quantum choreobotics, an interactive dance-theater performance where audiences influence robot movements to engage with quantum technology concepts. The project uses art and performance to make complex scientific ideas accessible and thought-provoking for the public.
Principal Investigator(s): Bill Kules
Funders: UMD Funded
Research Areas: Data Science, Analytics, and Visualization Digital Humanities Health Informatics Human-Computer Interaction Machine Learning, AI, Computational Linguistics, and Information Retrieval
UMD researchers Bill Kules and Huaishu Peng are exploring quantum choreobotics, an interactive dance-theater performance where audiences influence robot movements to engage with quantum technology concepts. The project uses art and performance to make complex scientific ideas accessible and thought-provoking for the public.
SaTC: CORE: Medium: Collaborative: BaitBuster 2.0: Keeping Users Away From Clickbait
Principal Investigator(s): Naeemul Hassan
Funders: National Science Foundation
Research Areas: Machine Learning, AI, Computational Linguistics, and Information Retrieval Data Privacy and Sociotechnical Cybersecurity Data Science, Analytics, and Visualization Social Networks, Online Communities, and Social Media
Developing novel techniques - through the application of state-of-the-art machine learning - to detect various forms of clickbait, especially video-based clickbait, and study user behavior on social media to design effective warning systems.
Principal Investigator(s): Naeemul Hassan
Funders: National Science Foundation
Research Areas: Machine Learning, AI, Computational Linguistics, and Information Retrieval Data Privacy and Sociotechnical Cybersecurity Data Science, Analytics, and Visualization Social Networks, Online Communities, and Social Media
Developing novel techniques - through the application of state-of-the-art machine learning - to detect various forms of clickbait, especially video-based clickbait, and study user behavior on social media to design effective warning systems.
SaTC: CORE: Medium: Learning Code(s): Community-Centered Design of Automated Content Moderation
Principal Investigator(s): Katie Shilton
Funders: National Science Foundation
Research Areas: Machine Learning, AI, Computational Linguistics, and Information Retrieval Social Networks, Online Communities, and Social Media
This research project aims to improve online community moderation by using machine learning and natural language processing. It focuses on learning from existing community decisions, supporting moderators, and creating adaptable tools. The goal is healthier online spaces and better working conditions for moderators.
Principal Investigator(s): Katie Shilton
Funders: National Science Foundation
Research Areas: Machine Learning, AI, Computational Linguistics, and Information Retrieval Social Networks, Online Communities, and Social Media
This research project aims to improve online community moderation by using machine learning and natural language processing. It focuses on learning from existing community decisions, supporting moderators, and creating adaptable tools. The goal is healthier online spaces and better working conditions for moderators.
Testbed for the Redlining Archives of California’s Exclusionary Spaces (T-RACES)
Principal Investigator(s): Richard Marciano
Funders: Unfunded
Research Areas: Archival Science Data Science, Analytics, and Visualization Library and Information Science Machine Learning, AI, Computational Linguistics, and Information Retrieval
Making publicly accessible online documents relating to the practice of “redlining” neighborhoods in the 1930s and 1940s in eight California cities. “Redlining” refers to the practice of flagging minority neighborhoods as undesirable for home loans. The project creates a searchable database and interactive map interface.
Principal Investigator(s): Richard Marciano
Funders: Unfunded
Research Areas: Archival Science Data Science, Analytics, and Visualization Library and Information Science Machine Learning, AI, Computational Linguistics, and Information Retrieval
Making publicly accessible online documents relating to the practice of “redlining” neighborhoods in the 1930s and 1940s in eight California cities. “Redlining” refers to the practice of flagging minority neighborhoods as undesirable for home loans. The project creates a searchable database and interactive map interface.