arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2401.16541cs.CLcs.AI
收藏

GuReT:区分与内疚和后悔相关的文本

GuReT: Distinguishing Guilt and Regret related Text

Institute for the Future of Education, Tecnológico de Monterrey(蒙特雷理工学院未来教育研究所);Instituto Politécnico Nacional, Centro de Investigación en Computación(国立理工学院计算机研究中心);The University of Texas at Austin(德克萨斯大学奥斯汀分校)

Sabur Butt, Fazlourrahman Balouchzahi, Abdul Gafar Manuel Meque, Maaz Amjad, Hector G. Ceballos Cancino, Grigori Sidorov, Alexander Gelbukh

AI总结:

本研究针对情感计算中内疚与后悔情绪区分研究不足的问题,构建专用数据集,采用机器学习与transformer模型及思维链等推理方法开展基准测试,验证了transformer模型的更优性能。

摘要:

人类决策与情绪(尤其是内疚和后悔)之间的复杂关系,对行为和幸福感有着重要影响。然而,这些情绪的细微差别与相互作用在计算模型中常被忽视。本文提出了一个专门用于剖析内疚与后悔的关系及其独特文本标记的数据集,填补了情感计算研究中的一项显著空白。我们的方法将内疚与后悔识别视为一项二分类任务,并采用3种机器学习技术和6种基于transformer的深度学习技术,在新创建的数据集上进行基准测试。本研究进一步采用了思维链、思维树等创新推理方法,以评估模型的解释逻辑。结果表明,基于transformer的模型性能优势明显,其宏F1分数达到90.4%,而表现最佳的机器学习分类器的宏F1分数为85.3%,证明了前者在区分复杂情绪状态方面的优越能力。

英文摘要:

The intricate relationship between human decision-making and emotions, particularly guilt and regret, has significant implications on behavior and well-being. Yet, these emotions subtle distinctions and interplay are often overlooked in computational models. This paper introduces a dataset tailored to dissect the relationship between guilt and regret and their unique textual markers, filling a notable gap in affective computing research. Our approach treats guilt and regret recognition as a binary classification task and employs three machine learning and six transformer-based deep learning techniques to benchmark the newly created dataset. The study further implements innovative reasoning methods like chain-of-thought and tree-of-thought to assess the models interpretive logic. The results indicate a clear performance edge for transformer-based models, achieving a 90.4% macro F1 score compared to the 85.3% scored by the best machine learning classifier, demonstrating their superior capability in distinguishing complex emotional states.

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。

↑