RetroChat: Designing for the Preservation of Past Digital Experiences

TL;DR

This paper presents RetroChat, an interactive archiving system using GPT-driven agents to preserve and evoke nostalgia for early Chinese social media conversations from 2000-2010.

Contribution

It introduces a novel experiential archiving method that uses generative AI to emulate past digital communication styles for cultural preservation.

Findings

Participants experienced nostalgia and memory recall through the chat interface.

The system successfully emulated the language style of early Chinese social media.

Users adapted their language to match the agent's style, enhancing engagement.

Abstract

Rapid changes in social networks have transformed the way people express themselves, turning past neologisms, values, and mindsets embedded in these expressions into online heritage. How can we preserve these expressions as cultural heritage? Instead of traditional archiving methods for static material, we designed an interactive and experiential form of archiving for Chinese social networks. Using dialogue data from 2000-2010 on early Chinese social media, we developed a GPT-driven agent within a retro chat interface, emulating the language and expression style of the period for interaction. Results from a qualitative study with 18 participants show that the design captures the past chatting experience and evokes memory flashbacks and nostalgia feeling through conversation. Participants, particularly those familiar with the era, adapted their language to match the agent's chatting style. This study explores how the design of preservation methods for digital experiences can be informed by experiential representations supported by generative tools.