Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

AI Cat Narrator: Designing an AI Tool for Exploring the Shared World and Social Connection with a Cat

Zhenchi Lai, Janet Yi-Ching Huang, Rung-Huei Liang

TL;DR

The paper addresses how to rethink human-cat interactions by placing the cat's viewpoint into an ethnographic-fusion framework. It combines real-world cat-perspective data with fictional text via defamiliarization and trains using ChatGPT GPTs to produce alternative narratives. The key contributions are a dual-database training setup (A: factual; B: augmented with pet phrases and cat fiction), a GAN-inspired AI Evaluator to refine outputs, and a practical workflow for collecting cat-centered data. The work demonstrates that integrating fiction with real data yields empathetic, individualized cat narratives and offers a design-oriented tool for future smart living spaces that accommodate both humans and cats.

Abstract

As technology continues to advance, the interaction between humans and cats is becoming more diverse. Our research introduces a new tool called the AI Cat Narrator, which offers a unique perspective on the shared lives of humans and cats. We combined the method of ethnography with fictional storytelling, using a defamiliarization strategy to merge real-world data seen through the eyes of cats with excerpts from cat literature. This combination serves as the foundation for a database to instruct the AI Cat Narrator in crafting alternative narrative. Our findings indicate that using defamiliarized data for training purposes significantly contributes to the development of characters that are both more empathetic and individualized. The contributions of our study are twofold: 1) proposing an innovative approach to prompting a reevaluation of living alongside cats; 2) establishing a collaborative, exploratory tool developed by humans, cats, and AI together.

AI Cat Narrator: Designing an AI Tool for Exploring the Shared World and Social Connection with a Cat

TL;DR

The paper addresses how to rethink human-cat interactions by placing the cat's viewpoint into an ethnographic-fusion framework. It combines real-world cat-perspective data with fictional text via defamiliarization and trains using ChatGPT GPTs to produce alternative narratives. The key contributions are a dual-database training setup (A: factual; B: augmented with pet phrases and cat fiction), a GAN-inspired AI Evaluator to refine outputs, and a practical workflow for collecting cat-centered data. The work demonstrates that integrating fiction with real data yields empathetic, individualized cat narratives and offers a design-oriented tool for future smart living spaces that accommodate both humans and cats.

Abstract

As technology continues to advance, the interaction between humans and cats is becoming more diverse. Our research introduces a new tool called the AI Cat Narrator, which offers a unique perspective on the shared lives of humans and cats. We combined the method of ethnography with fictional storytelling, using a defamiliarization strategy to merge real-world data seen through the eyes of cats with excerpts from cat literature. This combination serves as the foundation for a database to instruct the AI Cat Narrator in crafting alternative narrative. Our findings indicate that using defamiliarized data for training purposes significantly contributes to the development of characters that are both more empathetic and individualized. The contributions of our study are twofold: 1) proposing an innovative approach to prompting a reevaluation of living alongside cats; 2) establishing a collaborative, exploratory tool developed by humans, cats, and AI together.
Paper Structure (6 sections, 2 figures)

This paper contains 6 sections, 2 figures.

Table of Contents

  1. Personalized AI Cat Narrator
  2. Data Collection
  3. Training of AI Cat Narrator
  4. Preliminary Training Results
  5. Discussion & Future Work
  6. Conclusion

Figures (2)

  • Figure 1: The Training Procedure of the AI Cat Narrator
  • Figure 2: The figure showcases the different outcomes of sentences generated by two versions of the AI Cat Narrator, each using distinct databases. AI Cat Narrator (A) produces narratives based on factual data stored in its database. On the other hand, AI Cat Narrator (B) integrates counterfactual data such as pet phrases and the sentences from cat fiction, resulting in narratives that include relevant descriptions from these sources. Sentences in AI Cat Narrator (B) that are linked to novels and catchphase are highlighted with yellow color to emphasize their inclusion.