Simple Summary Understanding how animals feel is essential for improving their welfare and strengthening their bond with humans. In this study, we explored how GPT-4, an advanced AI tool, can detect emotions in pets by analyzing their pictures. Our research had two main steps. First, we tested the AI tool on a variety of animals like cats and rabbits, but the accuracy was moderate. Then, we focused only on dogs, refining the instructions given to the AI tool, which led to much better results. The AI tool was able to recognize emotions like happiness, sadness, and anger in dogs with high accuracy. By examining how the AI tool explained its predictions, we learned about its strengths and where it struggled, especially with emotions that were harder to differentiate. This research shows how AI can help us better understand animals and create tools to support their well-being.
Generative AI Meets Animal Welfare: Evaluating GPT-4 for Pet Emotion Detection
Bekir Çetintav,Yavuz Selim Guven,Engincan Gulek,A. Akbaş
Published 2025 in Animals
ABSTRACT
PUBLICATION RECORD
- Publication year
2025
- Venue
Animals
- Publication date
2025-02-01
- Fields of study
Medicine, Computer Science, Environmental Science
- Identifiers
- External record
- Source metadata
Semantic Scholar, PubMed
CITATION MAP
EXTRACTION MAP
CLAIMS
- No claims are published for this paper.
CONCEPTS
- No concepts are published for this paper.
REFERENCES
Showing 1-21 of 21 references · Page 1 of 1
CITED BY
Showing 1-5 of 5 citing papers · Page 1 of 1