Lei, K. (CMPM) – Designing for Meaningful Large-Scale Online Communication, Connection, and Collective Insight

Digital technologies have made large-scale online interaction a central part of how people communicate, connect, and work together. Yet scaling often comes at the cost of depth, and interactions can become superficial and chaotic, drifting away from the richer interactional contexts of small-scale or in-person settings that support trust and meaningful exchange, and that make it possible for participants to respond to and build constructively on one another’s ideas. Although recent advances such as large language models have opened new possibilities for shaping online interaction, there has been relatively little exploration of how to design interaction mechanisms that take advantage of large-scale engagement while fostering interactions that are engaged, authentic, connected, and generative.

In this dissertation, I explore how large-scale online systems can be designed to support engaged and meaningful interaction at scale from three distinct angles: creating few-to-many conversation structures that enable broad participation while maintaining coherence and a high level of engagement; fostering authentic self-expression in ways that build connection; and designing mechanisms that allow participants to interpret and constructively build on one another’s contributions to generate collective insight. I begin by designing a chat-based interface that organizes conversations through multi-person conversational units, enabling one or a few mentors to effectively mentor a large-group of students. I then examine how to design a gratitude-focused online community that supports authentic and positive expressions of gratitude, cultivating positive cycles of reflection and connection. Finally, I introduce a large language model–powered survey platform that blends qualitative depth, quantitative structure, and collaborative interaction, enabling respondents to engage with and build on each other’s ideas while providing survey creators with richer and more interpretable results. My work demonstrates how technological affordances and large-scale participation can be combined to create interaction mechanisms that support the move from isolated contributions toward shared understanding, offering unique forms of engagement that small-scale or in-person settings cannot provide.

Event Host: Kehua Lei, PhD Candidate, Computational Media

Advisor: David Lee