arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2311.09602cs.CL
收藏

语言模型(通常)在预测情感时不考虑情感触发因素

Language Models (Mostly) Do Not Consider Emotion Triggers When Predicting Emotion

The University of Texas at Austin(得克萨斯大学奥斯汀分校);University of Illinois Chicago(伊利诺伊大学芝加哥分校)

Smriti Singh, Cornelia Caragea, Junyi Jessy Li

AI总结:

本研究引入EmoTrigger数据集评估大型语言模型识别情感触发因素的能力,发现模型在预测情感时通常不考虑情感触发因素,而是依赖特征间的复杂相互作用。

摘要:

情境和事件会引发人类的情感,但它们在多大程度上为情感检测模型的预测提供了信息?本研究调查了人工标注的情感触发因素与模型在预测情感时认为显著的特征之间的相关性。首先,我们引入了一个新数据集EmoTrigger,包含来自三个不同数据集的900篇社交媒体帖子;这些帖子由专家标注了情感触发因素,且具有高一致性。使用EmoTrigger,我们评估了大型语言模型(LLMs)识别情感触发因素的能力,并对LLMs和微调模型之间被认为对这些任务重要的特征进行了比较分析。我们的分析表明,情感触发因素在很大程度上不被视为情感预测模型的显著特征,相反,各种特征与情感检测任务之间存在复杂的相互作用。

英文摘要:

Situations and events evoke emotions in humans, but to what extent do they inform the prediction of emotion detection models? This work investigates how well human-annotated emotion triggers correlate with features that models deemed salient in their prediction of emotions. First, we introduce a novel dataset EmoTrigger, consisting of 900 social media posts sourced from three different datasets; these were annotated by experts for emotion triggers with high agreement. Using EmoTrigger, we evaluate the ability of large language models (LLMs) to identify emotion triggers, and conduct a comparative analysis of the features considered important for these tasks between LLMs and fine-tuned models. Our analysis reveals that emotion triggers are largely not considered salient features for emotion prediction models, instead there is intricate interplay between various features and the task of emotion detection.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑