"AI Afterlife" as Digital Legacy: Perceptions, Expectations, and Concerns
Ying Lei, Shuai Ma, Yuling Sun, Xiaojuan Ma
TL;DR
This paper investigates perceptions, expectations, and concerns toward AI Afterlife as digital legacy from the perspective of individuals represented by AI-generated agents. It adopts a qualitative approach with 18 participants from diverse Chinese backgrounds and employs thematic analysis to reveal how attitudes are shaped by personal, familial, technological, and societal factors, as well as how AI Afterlife differs from traditional digital legacy. The study identifies design implications across the life cycle (encode-access-dispossess) and interaction dimensions (replication-simulation-reactivity) to maintain identity consistency and balance intrusiveness with support. It also highlights key concerns around technology, mental health, security, and socioeconomic impacts, offering guidance for researchers and designers to address ethical and practical challenges in deploying AI-generated digital legacies.
Abstract
The rise of generative AI technology has sparked interest in using digital information to create AI-generated agents as digital legacy. These agents, often referred to as "AI Afterlives", present unique challenges compared to traditional digital legacy. Yet, there is limited human-centered research on "AI Afterlife" as digital legacy, especially from the perspectives of the individuals being represented by these agents. This paper presents a qualitative study examining users' perceptions, expectations, and concerns regarding AI-generated agents as digital legacy. We identify factors shaping people's attitudes, their perceived differences compared with the traditional digital legacy, and concerns they might have in real practices. We also examine the design aspects throughout the life cycle and interaction process. Based on these findings, we situate "AI Afterlife" in digital legacy, and delve into design implications for maintaining identity consistency and balancing intrusiveness and support in "AI Afterlife" as digital legacy.