Understanding sentiment in multimodal conversations is a complex yet crucial challenge toward building emotionally intelligent AI systems. The Multimodal Conversational Aspect-based Sentiment Analysis (MCABSA) Challenge invited participants to tackle two demanding subtasks: (1) extracting a comprehensive sentiment sextuple, including holder, target, aspect, opinion, sentiment, and rationale from multi-speaker dialogues, and (2) detecting sentiment flipping, which detects dynamic sentiment shifts and their underlying triggers. For Subtask-I, in the present paper, we designed a structured prompting pipeline that guided large language models (LLMs) to sequentially extract sentiment components with refined contextual understanding. For Subtask-II, we further leveraged the complementary strengths of three LLMs through ensembling to robustly identify sentiment transitions and their triggers. Our system achieved a 47.38% average score on Subtask-I and a 74.12% exact match F1 on Subtask-II, showing the effectiveness of step-wise refinement and ensemble strategies in rich, multimodal sentiment analysis tasks.

翻译：理解多模态对话中的情感是构建情感智能AI系统所面临的一项复杂而关键的挑战。多模态对话方面情感分析（MCABSA）挑战赛要求参与者完成两个高难度子任务：（1）从多说话者对话中提取完整的情感六元组，包括持有者、目标、方面、意见、情感及依据；（2）检测情感翻转，即识别动态情感转变及其潜在触发因素。针对子任务一，本文设计了一种结构化提示流程，引导大语言模型（LLM）通过细化的上下文理解顺序提取情感要素。对于子任务二，我们进一步通过集成三种LLM的互补优势，以稳健识别情感转变及其触发因素。我们的系统在子任务一上取得了47.38%的平均得分，在子任务二上获得了74.12%的精确匹配F1值，证明了逐步优化与集成策略在复杂多模态情感分析任务中的有效性。