Research

My research lies at the intersection of Human-Computer Interaction (HCI), Intelligent User Interface (IUI), and Artificial Intelligence (AI). My work seeks to develop fair, trustworthy, transparent AI using the data-driven and human-centered computing (HCC) approaches, particularly for recommender systems, healthcare systems, and social media. I adopt mixed, quantitative, and qualitative approaches to understand users’ interaction and experience with AI-driven systems and explore design solutions for building trustworthy services and improving human-AI interaction. I am specifically interested in designing solutions for empowering non-expert users and marginalized groups. My research could broadly be defined as twofold: first, I aim to generate empirical, conceptual, and theoretical insights into how AI-driven systems users engage in information retrieval, seeking, and personal decision-making; second, my work offers practical recommendations for designing a better controllable and explainable AI (XAI) mechanism to support and empower individuals’ interactions with the AI systems.

Project 1. Conversational & Explainable AI

Research has demonstrated that providing explanations about recommendation systems positively affects users' experiences. Accordingly, developers have adopted many explainable recommendation models and interfaces in applications such as social media. However, these explanations are not personalized to users with varied digital literacy or computational knowledge and may not always ensure users understand the underlying rationale contributing to data or algorithms. I argue that explainable AI research should consider cross-discipline knowledge (e.g., HCI, social science, cognitive science, psychology, etc.) and the user's mental model instead of only the domain expert’s scientific intuition. I want to explore how to design explainable AI that could be used to empower human-AI interaction across socio-technical systems. This project fills this research gap by exploring the dynamic process of a user's understanding of an AI-based, explainable recommender system and how this understanding evolves. In addition, it extends the existing research horizon on explainable recommender systems by investigating a novel conversational interaction between people and target systems. Finally, this work will enable a new ecosystem through a unified research program consisting of modeling explanation strategies for different users and exploring and developing practical system prototypes. The project's success will deepen the scientific understanding of designing and implementing fair and transparent everyday use AI systems for users of varied backgrounds and expertise. For instance, users may seek personalized explanations from a health recommendation system and make informed decisions based on transparency and comprehension.


Project 2. Conversational AI in Healthcare

This project explores the effects of promoting community health access through Explainable AI-mediated Communication (XAI-MC). My approach is to mediate communication between healthcare providers (e.g., OB-GYN, healthcare coordinators) and patients (e.g., pregnant women) through a self-explained transparent computational agent. Specifically, I proposed to build AI-powered Smart Chatbot (SC) to improve health access, awareness, and literacy in underserved populations. The AI-based SC can book appointments, remind patients to take their pills, improve patients to promote a healthy lifestyle, monitor patients’ status, answer patients’ questions and perform other time-intensive tasks. This project investigates two primary research questions: 1) How do SCs support healthy practices within underserved populations? and 2) How do SCs promote community health access, awareness, and literacy? I would adopt a mixed method to answer these research questions by collecting quantitative and qualitative data with three aims. This project would collaborate with an Omaha local community group and UNMC that exclusively provides maternal wellness services for underserved black populations. The long-term objective of this research is to develop and study AI-based SCs designed to encourage healthy diet choices in women throughout pregnancy.

Project 3. HCI & Social Computing

My multidisciplinary training and diverse methods support me with high flexibility and adaptability in discovering new research topics, collaborating with researchers from various disciplinary backgrounds, and conducting user experiments with external constraints such as the COVID-19 pandemic. I have collaborated with HCI researchers on various topics such as social diversity to crisis informatics for understanding marginalized groups' reaction to the COVID-19 pandemic, health informatics for improving medical and health decisions, enhancing accessibility for people with visual impairment using remote sighted assistance, and assisting citizen scientists for monitoring local water quality.