NLP datasets are richer than just input-output pairs; rather, they carry causal relations between the input and output variables. In this work, we take sentiment classification as an example and look into the causal relations between the review (X) and sentiment (Y). As psychology studies show that language can affect emotion, different psychological processes are evoked when a person first makes a rating and then self-rationalizes their feeling in a review (where the sentiment causes the review, i.e., Y -> X), versus first describes their experience, and weighs the pros and cons to give a final rating (where the review causes the sentiment, i.e., X -> Y ). Furthermore, it is also a completely different psychological process if an annotator infers the original rating of the user by theory of mind (ToM) (where the review causes the rating, i.e., X -ToM-> Y ). In this paper, we verbalize these three causal mechanisms of human psychological processes of sentiment classification into three different causal prompts, and study (1) how differently they perform, and (2) what nature of sentiment classification data leads to agreement or diversity in the model responses elicited by the prompts. We suggest future work raise awareness of different causal structures in NLP tasks. Our code and data are at https://github.com/cogito233/psych-causal-prompt

翻译：自然语言处理数据集不仅包含输入-输出对，更承载着输入变量与输出变量之间的因果关联。本研究以情感分类为例，深入探究评论（X）与情感（Y）之间的因果关联。心理学研究表明，语言能够影响情绪：当个体先给出评分再在评论中自我合理化其感受时（即情感引发评论，Y→X），与先描述体验、权衡利弊后给出最终评分时（即评论引发情感，X→Y），会引发截然不同的心理过程。此外，若标注者通过心智理论（ToM）推断用户的原始评分（即评论引发评分，X-ToM→Y），同样属于完全不同的心理过程。本文针对情感分类中人类心理过程的三种因果机制，将其表述为三种不同的因果提示，研究：（1）三种机制表现差异如何；（2）哪些情感分类数据特性会导致各提示引发的模型响应呈现一致性或多样性。我们建议未来研究应关注NLP任务中不同的因果结构。代码与数据见：https://github.com/cogito233/psych-causal-prompt