用三种方法建模文本情绪变化，实测近期情绪轨迹比文字语义更重要。
UKP_Psycontrol at SemEval-2026 Task 2: Modeling Valence and Arousal Dynamics from Text
- 结合大模型提示与结构化转移模型，融合用户特征与情绪轨迹。
- 在两个子任务中均获第一，证明数值情绪路径比文本内容更关键。
- 适合做情绪动态分析、社交媒体情感追踪的研究者参考。
本文介绍我们为 SemEval-2026 任务 2 开发的系统。该任务要求对时序排列的用户生成文本进行当前情绪状态及短期情绪变化建模。我们探索了三种互补方法：(1) 在用户感知与非感知设置下使用大语言模型（LLM）提示；(2) 采用具有伊辛模型式相互作用的成对最大熵（MaxEnt）模型进行结构化转移建模；(3) 一个轻量级神经回归模型，融合近期情绪轨迹与可训练的用户嵌入。实验结果表明，大模型能有效捕捉文本中的静态情绪信号，而本数据集中短期情绪波动主要由近期数值情绪轨迹解释，而非文本语义。我们的系统在官方评估指标下于子任务1和子任务2A均排名第一。
原文摘要 · Abstract (English)
This paper presents our system developed for SemEval-2026 Task 2. The task requires modeling both current affect and short-term affective change in chronologically ordered user-generated texts. We explore three complementary approaches: (1) LLM prompting under user-aware and user-agnostic settings, (2) a pairwise Maximum Entropy (MaxEnt) model with Ising-style interactions for structured transition modeling, and (3) a lightweight neural regression model incorporating recent affective trajectories and trainable user embeddings. Our findings indicate that LLMs effectively capture static affective signals from text, whereas short-term affective variation in this dataset is more strongly explained by recent numeric state trajectories than by textual semantics. Our system ranked first among participating teams in both Subtask 1 and Subtask 2A based on the official evaluation metric.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。