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. Our code is open at https://github.com/scofield7419/THOR-ISA.

翻译：情感分析系统试图基于输入文本中的关键观点表达来确定给定目标的情感极性，而在隐式情感分析中，观点线索以隐晦且模糊的方式呈现。因此，检测隐式情感需要具备常识和多跳推理能力，以推断观点的潜在意图。受近期思维链思想的启发，本文提出了一种三跳推理思维链框架，以模拟人类推理过程进行隐式情感分析。我们为THOR设计了三步提示原则，逐步推导出隐式方面、观点，最终得到情感极性。我们的THOR+Flan-T5（11B）在监督设置下将最先进水平的F1值提升了超过6%。更引人注目的是，THOR+GPT3（175B）在零样本设置下将最先进水平的F1值提升了超过50%。我们的代码已在https://github.com/scofield7419/THOR-ISA开源。