Reasoning Implicit Sentiment with Chain-of-Thought Prompting

Hao Fei, Bobo Li, Qian Liu, Lidong Bing, Fei Li, Tat-Seng Chua


Abstract
While sentiment analysis systems try to determine the sentiment polarities of given targets based on the key opinion expressions in input texts, in implicit sentiment analysis (ISA) the opinion cues come in an implicit and obscure manner. Thus detecting implicit sentiment requires the common-sense and multi-hop reasoning ability to infer the latent intent of opinion. Inspired by the recent chain-of-thought (CoT) idea, in this work we introduce a Three-hop Reasoning (THOR) CoT framework to mimic the human-like reasoning process for ISA. We design a three-step prompting principle for THOR to step-by-step induce the implicit aspect, opinion, and finally the sentiment polarity. Our THOR+Flan-T5 (11B) pushes the state-of-the-art (SoTA) by over 6% F1 on supervised setup. More strikingly, THOR+GPT3 (175B) boosts the SoTA by over 50% F1 on zero-shot setting.
Anthology ID:
2023.acl-short.101
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1171–1182
Language:
URL:
https://aclanthology.org/2023.acl-short.101
DOI:
Bibkey:
Cite (ACL):
Hao Fei, Bobo Li, Qian Liu, Lidong Bing, Fei Li, and Tat-Seng Chua. 2023. Reasoning Implicit Sentiment with Chain-of-Thought Prompting. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 1171–1182, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Reasoning Implicit Sentiment with Chain-of-Thought Prompting (Fei et al., ACL 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nodalida-main-page/2023.acl-short.101.pdf