Facilitating Visual Analytics with ChatGPT: 2023 VAST Challenge Award - Application of LLMs to Support VA Process

To solve the VAST Challenge 2023 MC3, our team employed a large language model, ChatGPT, to explore the potential of AI -guided visual analytics for the detection of anomalies within a knowledge graph in the context of illegal fishing and marine trade. We employed a systematic and iterative approach...

Full description

Saved in:

Bibliographic Details
Published in:	2023 VAST Challenge pp. 5 - 6
Main Authors:	Zhao, Ava, Su, Zhanqi, Fei, Bill, Zhuo, Na, Wang, Hao, Yu, Tianzhou, Li, Zuotian, Qian, Cheryl, Chen, Yingjie Victor
Format:	Conference Proceeding
Language:	English
Published:	IEEE 22-10-2023
Subjects:	AI Language Model Assisted Learning ChatGPT Collaboration Knowledge GraphMarine Trade Manuals Refining Scalability Systematics Visual analytics Writing
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	To solve the VAST Challenge 2023 MC3, our team employed a large language model, ChatGPT, to explore the potential of AI -guided visual analytics for the detection of anomalies within a knowledge graph in the context of illegal fishing and marine trade. We employed a systematic and iterative approach, guided by GPT augmentation, that enabled problem understanding, data processing, solution exploration, code writing, and results analysis. By generating and analyzing various graphs, we identified anomalies related to revenue and product services. Further analyses unveiled potential illegal fishing activities and identified instances warranting additional investigation. Overall, our work highlights both the strengths and limitations of ChatGPT in aiding the visual analytics process and emphasizes the importance of human judgment in refining AI-generated outputs.
DOI:	10.1109/VASTChallenge60523.2023.00008