Understanding the Design Taxonomy of AI-Mediated Interpersonal Communication Experiences in HCI: A Scoping Analysis

Interpersonal communication is a fundamental aspect of everyday life, shaping interactions across workplaces, education, entertainment, healthcare, and beyond. While computer-mediated communication has been extensively studied, a comprehensive understanding of AI-Mediated Interpersonal Communication (AIMIC) remains lacking. An in-depth scoping analysis is urgently needed to understand the research landscape of AIMIC in HCI, particularly following the release of ChatGPT, the rapid growth of large foundation models, and AI agent research. We conducted a comprehensive scoping analysis to understand AIMIC by performing an in-depth review of prior HCI literature published over the past decade (January, 2016 - May, 2026). Grounded in the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) approach, we curated 52 full-paper publications from the HCI literature spanning a range of interpersonal communication contexts. We analyzed this corpus by examining the types of AIMIC studied, AI integration approaches and human-AI interaction design, reported outcomes and benefits, as well as key challenges and future research opportunities.

Introduction. Far from a mere exchange of information, interpersonal communication is the indispensable currency of the modern world, spanning across workspace, education, entertainment, healthcare and beyond. Advances in digital tools and the internet have enabled a wide range of forms of Computer-Mediated Communication (CMC). CMC manifests in various ways, as described in the longstanding Computer Supported Cooperative Work (CSCW) matrix, which organizes communication along the dimension of time and space [51, 98]. CMC can occur in dyadic settings between two people or within larger groups. Furthermore, the communication experience can be in-person or distributed, and take place either synchronously or asynchronously. Facilitating engaging and effective conversation presents several challenges. For example, participants often struggle to connect when there is a significant information asymmetry or a lack of shared background knowledge; as the number of participants grows, ensuring inclusivity becomes increasingly difficult due to the complexities of the ‘many-mind problem’ [25].

Discussion / Conclusion. Our analysis characterizes AIMIC along four perspectives: the forms of AIMIC studied (RQ1), how AI is integrated and how human-AI interaction is designed (RQ2), the outcomes and benefits these systems target (RQ3), and the challenges and opportunities the field has surfaced (RQ4). Our findings point to broader shifts in how HCI researchers conceive of AI’s role in interpersonal communication. Our implications are organized into four areas. A shift in AI’s role as a passive channel to an active communication participant. Despite the growth in publication volume (Figure 3), one clearest trend unveiled in our analysis is a qualitative shift in what AI is asked to do. Pre-2023 systems predominantly relied on rule-based agents and classifier pipelines to extract, surface, or lightly reformat information that a human still authored and sent (RQ2).