学生情感与行为分析对于提升学习效果、实现教育体验个性化至关重要。传统方法常依赖侵入式的视觉和生理数据采集,存在隐私隐患与可扩展性问题。本文提出一种利用大语言模型(large language models, LLMs)与提示工程分析学生文本数据的新方法。该方法采用定制化提示引导LLM识别情感与参与状态,提供了一种非侵入式、可扩展的解决方案。我们使用Qwen、ChatGPT、Claude2、GPT-4开展实验,将所提方法与基线模型、思维链(chain-of-thought, CoT)提示法进行对比。结果表明,该方法在准确率和上下文理解能力上均显著优于基线模型。本研究凸显了LLM结合提示工程可为教育情感与行为分析提供实用有效工具的潜力。
英文摘要:
The analysis of students' emotions and behaviors is crucial for enhancing learning outcomes and personalizing educational experiences. Traditional methods often rely on intrusive visual and physiological data collection, posing privacy concerns and scalability issues. This paper proposes a novel method leveraging large language models (LLMs) and prompt engineering to analyze textual data from students. Our approach utilizes tailored prompts to guide LLMs in detecting emotional and engagement states, providing a non-intrusive and scalable solution. We conducted experiments using Qwen, ChatGPT, Claude2, and GPT-4, comparing our method against baseline models and chain-of-thought (CoT) prompting. Results demonstrate that our method significantly outperforms the baselines in both accuracy and contextual understanding. This study highlights the potential of LLMs combined with prompt engineering to offer practical and effective tools for educational emotion and behavior analysis.
NegativePrompt: Leveraging Psychology for Large Language Models Enhancement via Negative Emotional Stimuli
School of Artificial Intelligence, Jilin University(吉林大学人工智能学院);Institute of Software, CAS(中国科学院软件研究所);Microsoft Research Asia(微软亚洲研究院);Key Laboratory of Symbolic Computation and Knowledge Engineering, Jilin University(吉林大学符号计算与知识工程重点实验室);International Center of Future Science, Jilin University(吉林大学未来科学国际合作联合实验室)
EERPD: Leveraging Emotion and Emotion Regulation for Improving Personality Detection
State Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University(北京大学计算机学院多媒体信息处理国家重点实验室);School of Software, BNRist, Tsinghua University(清华大学软件学院北京信息科学与技术国家研究中心)
Cognitive networks reconstruct mindsets about STEM subjects and educational contexts in almost 1000 high-schoolers, University students and LLM-based digital twins
Department of Psychology and Cognitive Science, University of Trento(心理学与认知科学系,特伦托大学);Department of Psychology and Communication, University of Bari(心理学与传播系,巴里大学);Department of Physics, University of Trento(物理学系,特伦托大学)
From Rational Answers to Emotional Resonance: The Role of Controllable Emotion Generation in Language Models
State Key Laboratory on Technologies for Chinese Medicine Pharmaceutical Process Control and Intelligent Manufacture(中药制药过程控制与智能制造技术国家重点实验室);Zhejiang Lab(浙江实验室)
Leveraging Large Language Model as Simulated Patients for Clinical Education
Wangxuan Institute of Computer Technology, Peking University(北京大学王选计算机研究所);School of Computer Science, Wuhan University(武汉大学计算机学院);CureFun Co.(CureFun公司)
A Customer Journey in the Land of Oz: Leveraging the Wizard of Oz Technique to Model Emotions in Customer Service Interactions
Translation Technology Team, Ghent University(翻译技术团队,根特大学);IDLab, Internet technology and Data science Lab(IDLab,互联网技术与数据科学实验室);Data science Lab, Ghent University--imec(数据科学实验室,根特大学--imec)
本文通过Wizard of Oz实验构建EmoWOZ-CS语料库,评估基于WOZ的运营商引导情感轨迹设计,量化人类标注性能差异,并基准检测与前瞻性情绪推断在实时支持中的挑战。
Leveraging Emotion-specific Features to Improve Transformer Performance for Emotion Classification
PVG’s COET(PVG工程学院);Savitribai Phule Pune University(萨维特里巴伊·普勒·浦那大学)
本文描述了PVGs AI Club团队在WASSA 2022举行的情绪分类共享任务的方法。此轨道2子任务侧重于构建模型,该模型可以基于新闻文章中的文章预测多类情感标签,其中一个人,一个团体或另一个实体受到影响。基线Transformer模型在序列分类任务上表现出良好的效果,我们的目标是在集成技术的帮助下,并通过利用两种不同的情感表达来提高这种性能。我们观察到比我们的基线模型更好的结果,并在情感分类任务上实现了0.619的准确度和0.520的宏观F1得分。
Leveraging Label Correlations in a Multi-label Setting: A Case Study in Emotion
University of Southern California(南加州大学);Information Science Institute, University of Southern California(南加州大学信息科学研究所);Microsoft Cognitive Services(微软认知服务)
检测文本中表达的情感已经成为一系列领域的关键。在这项工作中,我们研究如何利用标签相关性的多标签情感识别模型,以提高情感检测。首先,我们开发了两种建模方法来解决这个问题,以捕捉情感词本身的词关联,通过在输入中包含情感,或者利用Masked Language Modeling(MLM)。其次,我们将情感表示的成对约束作为正则化项与模型的分类损失相结合。我们将这些术语分为两类,局部和全局。前者基于黄金标签动态变化,而后者在训练期间保持静态。我们使用基于单语BERT的模型在SemEval 2018任务1 E-c中展示了西班牙语,英语和阿拉伯语的最先进性能。在更好的性能之上,我们还展示了更好的鲁棒性。代码可在https://github.com/gchochla/Demux-MEmo上获得。
Leveraging Cross-Attention Transformer and Multi-Feature Fusion for Cross-Linguistic Speech Emotion Recognition
Shanghai Maritime University(上海海事大学);Carleton University(卡尔顿大学);The University of British Columbia(不列颠哥伦比亚大学);Stanford University(斯坦福大学);The University of North Carolina at Pembroke(北卡罗来纳大学彭布罗克分校)
MF-AED-AEC: Speech Emotion Recognition by Leveraging Multimodal Fusion, Asr Error Detection, and Asr Error Correction
Graduate School of Informatics, Nagoya University(名古屋大学信息学研究科);School of Computer Science and Technology, Hainan University(海南大学计算机科学与技术学院);Information Technology Center, Nagoya University(名古屋大学信息技术中心)