TMAK-Plus at SIGHAN-2024 dimABSA Task: Multi-Agent Collaboration for Transparent and Rational Sentiment Analysis

Xin Kang, Zhifei Zhang, 周嘉政 周嘉政, Raino.wu@dataarobotics.com Raino.wu@dataarobotics.com, 2020010107@mail.hfut.edu.cn 2020010107@mail.hfut.edu.cn, Kazuyuki Matsumoto


Abstract
The TMAK-Plus team proposes a Multi-Agent Collaboration (MAC) model for the dimensional Aspect-Based Sentiment Analysis (dimABSA) task at SIGHAN-2024. The MAC model leverages Neuro-Symbolic AI to solve dimABSA transparently and rationally through symbolic message exchanges among generative AI agents. These agents collaborate on aspect detection, opinion detection, aspect classification, and intensity estimation. We created 8 sentiment intensity agents with distinct character traits to mimic diverse sentiment perceptions and average their outputs. The AI agents received clear instructions and 20 training examples to ensure task understanding. Our results suggest that the MAC model is effective in solving the dimABSA task and offers a transparent and rational approach to understanding the solution process.
Anthology ID:
2024.sighan-1.10
Volume:
Proceedings of the 10th SIGHAN Workshop on Chinese Language Processing (SIGHAN-10)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Kam-Fai Wong, Min Zhang, Ruifeng Xu, Jing Li, Zhongyu Wei, Lin Gui, Bin Liang, Runcong Zhao
Venues:
SIGHAN | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
88–95
Language:
URL:
https://aclanthology.org/2024.sighan-1.10
DOI:
Bibkey:
Cite (ACL):
Xin Kang, Zhifei Zhang, 周嘉政 周嘉政, Raino.wu@dataarobotics.com Raino.wu@dataarobotics.com, 2020010107@mail.hfut.edu.cn 2020010107@mail.hfut.edu.cn, and Kazuyuki Matsumoto. 2024. TMAK-Plus at SIGHAN-2024 dimABSA Task: Multi-Agent Collaboration for Transparent and Rational Sentiment Analysis. In Proceedings of the 10th SIGHAN Workshop on Chinese Language Processing (SIGHAN-10), pages 88–95, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
TMAK-Plus at SIGHAN-2024 dimABSA Task: Multi-Agent Collaboration for Transparent and Rational Sentiment Analysis (Kang et al., SIGHAN-WS 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.sighan-1.10.pdf