Research
Affective Computing · Computational Psycholinguistics · Educational Technology
(Bridging emotion, language, and learning through intelligent design)
🧠 Research Overview
My research explores how artificial intelligence can assist emotional learning and cognitive reframing in language education.
Building upon my undergraduate thesis on lexical complexity in English writing, I now focus on how AI-driven narrative design and affective computing can help learners reshape their emotional attributions and reduce learning anxiety.
In essence, my work bridges linguistics, psychology, and human–computer interaction, aiming to design educational systems that heal as they teach — systems that understand emotion as deeply as they process language.
我的研究聚焦于 人工智能 如何在语言教育中促进 情绪学习 与 认知重构。
在本科论文探讨 英语写作词汇复杂度 的基础上，我进一步研究 AI 叙事设计 与 情感计算 如何帮助学习者修正 情绪归因，缓解 学习焦虑。
本研究跨越 语言学、心理学 与 人机交互，致力于设计能 在教学中治愈 的教育系统—— 一种既能理解语言，也能理解情感的智能系统。
🤖 Current Projects
AURA: AI for Understanding and Reframing Affect AURA: AI 辅助情绪理解与归因重构系统
AURA is an experimental prototype exploring how AI-driven dialogue systems can help students recognize and reframe their emotional attributions in real learning contexts.
The project integrates natural language processing, affective computing, and educational psychology to identify patterns of self-blame, anxiety, and motivation loss in student reflections — and to deliver empathetic, context-aware feedback.
The long-term vision of AURA is to create a modular emotional support system that extends beyond classrooms — supporting students, patients, and individuals experiencing psychological distress through adaptive, narrative-based AI interactions.
AURA 是一个实验性原型系统，用于探索 AI 对话系统 如何帮助学生在真实学习情境中识别并重构自己的 情绪归因。
项目融合了 自然语言处理、情感计算 与 教育心理学，识别学生反思文本中的 自责、焦虑 与 动机流失 模式， 并提供 具同理心且具语境意识的反馈。
AURA 的长期目标是构建一个 可模块化的情绪支持系统， 不仅服务于 课堂中的学生，也面向 患者 与 心理障碍人群， 通过 叙事驱动的自适应 AI 交互， 实现"让技术理解人类情感"的教育科技愿景。
📘 Undergraduate Thesis
The Effect of Task Type on Lexical Complexity in High School English Writing
My undergraduate thesis examined how different writing task types influence the lexical complexity of Chinese high school students' English compositions. Through corpus-based analysis and linguistic measurement, the research identified task-specific variations in vocabulary diversity, syntactic elaboration, and cognitive load.
This project laid the foundation for my current exploration of how language complexity relates to cognitive effort and emotional engagement, and how AI can assist in balancing these factors within educational settings.
我的本科毕业论文研究了不同写作任务类型对中国高中生英语作文词汇复杂度的影响。 通过语料库分析与语言学测量，本研究发现任务类型在词汇多样性、句法复杂度与认知负荷等方面存在显著差异。
该研究为我后续探索语言复杂度、认知努力与情绪参与之间的关系打下了理论基础， 并启发我进一步思考如何通过人工智能技术在教育情境中平衡学习效率与心理健康。