Reasoning Implicit Sentiment with Chain-of-Thought Prompting
Hao Fei, Bobo Li, Qian Liu, Lidong Bing, Fei Li, Tat-Seng Chua
Anthology
Underline
Main: Sentiment Analysis, Stylistic Analysis, and Argument Mining Main-poster Paper
Poster Session 5: Sentiment Analysis, Stylistic Analysis, and Argument Mining (Poster)
Conference Room: Frontenac Ballroom and Queen's Quay
Conference Time: July 11, 16:15-17:45 (EDT) (America/Toronto)
Global Time: July 11, Poster Session 5 (20:15-21:45 UTC)
Keywords:
argument mining
TLDR:
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 a...
You can open the
#paper-P468
channel in a separate window.
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.