Large language models (LLMs) offered opportunities for experimenting with the ideas involve building digital twin of humans as they are able to generate human like responses. This doctoral research leverages personas to develop digital persona twins as LLM-enabled conversational agents that simulate human actors in probation interview encounters for criminal justice training. By framing officers as information seekers and personas as dynamic information sources, my work enables scalable, ethical training tools for studying information interactions. A key innovation extends digital twin theory from continuous tracking to temporal snapshot instantiation, capturing a human actor’s information state at a specific moment to enable privacy-preserving simulation. This approach builds on personas to create diverse, individualized digital twins, opening new applications in social computing and information interaction. This dissertation aims to contribute empirical insights into professional information seeking behavior and validates new approaches for designing AI-mediated information sources that support skill development in high-stakes professional contexts.

Providing educational services to students with disabilities requires a unique combination of professional knowledge, and adherence to complex compliance and auditing goals. This study investigates the information access gaps within special education health services. Through think-aloud activities with therapy supervisors, practitioners, and administrative staff, we elicited explicit and implicit information needs, and identified significant challenges in current information seeking and documentation practices in this highly regulated environment. Thematic analysis of 329 coded segments (including 120 task descriptions, 123 pain points, and 86 desired features) reveals systematic mismatches between information capture and retrieval practices, which practitioners navigate daily, highlighting a necessity for information seeking beyond traditional search and demonstrating use cases for AI-augmented information retrieval. We present design implications, developed in collaboration with these stakeholders, focused on enhancing task documentation and designing interaction to support these needs, offering a roadmap for future information interaction systems in this complex, multi-stakeholder domain.

Understanding how social interactions affect privacy management is important in today’s digital landscape. We are investigating collective management of privacy and security through a mobile application, CO-oPS, that allows people to view and discuss each other’s app privacy settings within a community of users. Sixteen small, self-organized groups, totaling 81 participants, used the app over a four-week period. Data collection included pre- and post-study surveys measuring privacy perceptions (Community Belonging, Self-Efficacy, Community Collective Efficacy) along with in-app behavioral logs (messaging and viewing activity). In this paper, we present a social network analysis of our field study data, exploring the effects of group formation and engagement on building privacy and security efficacy through CO-oPS interactions. Our analysis reveals that while privacy perceptions were not initially homophilous, they grew more similar over time. Notably, proactively messaging others in the app enhanced personal privacy management confidence. Our results demonstrate the nuanced ways that groups can influence each other in addressing security and privacy needs.

Digital twins have been successfully used in various sectors to monitor performance, understand systemic problems, and evaluate solutions. However, their application in social contexts remains an emerging area of research. Gallup survey in 2023 reported that only 20% of Americans say they have a “great deal” of confidence in the US Criminal Justice system, and it makes exploring the potential usage of digital twins for advancing criminal justice an interesting social issue. Through a multidisciplinary focus group, this exploratory study investigated the challenges, potential benefits, and use cases for implementing digital twins in the US criminal justice system. The identified challenges are ethical issues, resistance to change, competing narratives, limitations of applying industrial perspectives to social issues, and power dynamics. Building digital twins in criminal justice can offer significant benefits, such as promoting equity and fairness, enhancing efficiency, resource optimization, and improving public safety. The study recognized the role of human-computer interaction in addressing these challenges and adapting digital twins for use in complex social systems. It recommends that policymakers consider a pilot project to test digital twins’ benefits.