PhD Student at Georgia Tech studying Human-Centered Computing (HCC) with a specialization in Human-Computer Interaction (HCI).
In my research, I explore the design and evaluation of explanations in Conversational AI systems and their role in aging in place for older adults and their caregivers. I'm interested in studying how different approaches to explainability and transparency in collaborative AI systems can improve the conversational user experience. My research interests include Human-AI Interaction, Explainable AI and designing for older adults. My doctoral advisors are Dr. Elizabeth Mynatt and Dr. Sonia Chernova in the School of Interactive Computing at Georgia Tech and my research is generously supported by Emory Healthcare's Brain Health Center and the NSF AI Institute for Collaborative Assistance and Responsive Interaction for Networked Groups (AI-CARING).
Education:
M.S. Human-Computer Interaction - Georgia Tech
B.Tech. Computer Science and Engineering - Vellore Institute of Technology
Publications
1. "Why did you say that?": Recommendations for Understanding Explainability in Conversational AI systems for Older Adults with MCI.
Niharika Mathur, Tamara Zubatiy, Elizabeth D. Mynatt
15th International Conference on Ubiquitous Computing and Ambient Intelligence UCAmI 2023, 6 pages.
2. “I don’t know how to help with that” - Learning from Limitations of Modern Conversational Agent Systems. Link
Tamara Zubatiy, Niharika Mathur, Larry Heck, Kayci Vickers, Agata Rozga, Elizabeth D. Mynatt
The 26th ACM Conference On Computer-Supported Cooperative Work and Social Computing (CSCW’23), 22 pages.
3. 🏆 [Best Paper Award] A Collaborative Approach to Support Medication Management in Older Adults with Mild Cognitive Impairment Using Conversational Assistants (CAs). Link
Niharika Mathur, Kunal Dhodapkar, Tamara Zubatiy, Jiachen Li, Brian D. Jones, Elizabeth D. Mynatt
The 24th International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS ’22), 14 pages.
4. Empowering Dyads of Older Adults With Mild Cognitive Impairment And Their Care Partners Using Conversational Agents. Link
Tamara Zubatiy, Kayci L. Vickers, Niharika Mathur, Elizabeth D. Mynatt
CHI Conference on Human Factors in Computing Systems (CHI ’21), 15 pages.
5. Sentiment analysis of the #MeToo movement using neutrosophy: Application of single-valued neutrosophic sets. Link
lanthenral Kandasamy, W.B. Vasantha, Niharika Mathur, Mayank Bisht, Florentin Smarandache
Optimization Theory Based on Neutrosophic and Plithogenic Sets, Academic Press, 2020, 18 pages.
Some featured projects -