Hemant Purohit, PhD

Hemant Purohit, PhD

Associate Professor

Volgenau School of Engineering

Other Positions:

Core Faculty

Research Theme:

Digital Technologies - Inventing new algorithms, digital techniques, and technologies

Key Interests:

Social Computing, Crisis Informatics, Human-AI Collaboration, Realtime Analytics, Applied Machine Learning, Knowledge Graphs, Humanitarian Technology, Public Safety

Education:

PhD, Computer Science and Engineering, Wright State University

Research Focus

Digital technologies such as social media, web, and the Internet of Things (IoT) have revolutionized information generation and consumption, generating massive unstructured data that presents an information overload challenge for sensemaking at any organization. Thus, my research interest is to mine relevant behaviors in online data at scale through the human-AI collaboration based intelligent/AI systems, which can augment human capabilities at organizational workplaces for processing realtime information for decision support. For example, creating realtime systems to filter data to discover people seeking help during disasters to aid emergency services. I create human-centered computing methods to extract and analyze individual/group behavioral knowledge (e.g., intentional acts) from text and multimedia data streams using Natural Language Processing, Computer Vision, and Machine Learning techniques. Our lab applies this research in a variety of domains to design AI systems for public services and social good, e.g., managing natural crises (hurricanes, etc), societal crises (hate, gender violence, etc.), and human crises (terrorism, cyberattacks, etc.).

Current Projects

■ NSF CRII Project: Creating algorithms for mining user intentions from natural language content, such as for seeking help on social media during disasters

■ NSF III Project: Designing computational summarization approaches to handle noisy, unstructured data streams from multiple online sources in real-time to transform into a structured and machine-readable format and augment decision support systems of emergency and public services, especially during disasters

■ NSF DUE Project: Analyzing social media participation as indicator of actors, awareness, attitudes, and activities related to STEM education and diversity

Select Publications

H. Purohit et al., Ranking and grouping social media requests for emergency services using serviceability model. Social Network Analysis and Mining, 10(1), 1-17 (2020).

H. Purohit et al., Intent mining for the good, bad, and ugly use of social web: concepts, methods, and challenges. In: Emerging Research Challenges and Opportunities in Computational Social Network Analysis and Mining, N. Agarwal, N. Dokoohaki, & S. Tokdemir, Ed. Cham: Springer International Publishing (2019).

J.L. Chan et al., Challenges to transforming unconventional social media data into actionable knowledge for public health systems during disasters. Disaster Medicine and Public Health Preparedness, 1-8 (2019).

 

College:

Volgenau School of Engineering

Contact Hemant:

Email: hpurohit@gmu.edu

LinkedIn: N/A