用大模型生成可解释的情感分析结果，提升社交媒体细粒度观点理解能力。
Explainable Multimodal Aspect-Based Sentiment Analysis with Dependency-guided Large Language Model
- 基于提示的生成范式，联合预测情感与自然语言解释。
- 依赖句法引导策略，提升对不同情感方面的区分能力。
- 适合需要可解释性分析的应用场景，如舆情监控与客服系统。
多模态方面级情感分析（MABSA）旨在通过联合建模文本与视觉信息，识别细粒度情感，对社交媒体中的观点理解至关重要。现有方法主要依赖复杂的多模态融合进行判别分类，但缺乏显式的解释能力。本文将MABSA重新定义为生成式且可解释的任务，提出统一框架：同时预测方面级情感并生成自然语言解释。基于多模态大语言模型（MLLMs），采用提示驱动的生成范式，联合生成情感与解释。为进一步增强面向方面的推理能力，提出依赖句法引导的情感线索策略：剪枝并文本化以方面为中心的依存句法树，引导模型区分不同情感方面，提升可解释性。为实现可解释性，利用MLLM构建含情感解释的新数据集用于微调。实验表明，该方法在情感分类准确率上持续提升，且生成的解释忠实、与方面对齐。
原文摘要 · Abstract (English)
Multimodal aspect-based sentiment analysis (MABSA) aims to identify aspect-level sentiments by jointly modeling textual and visual information, which is essential for fine-grained opinion understanding in social media. Existing approaches mainly rely on discriminative classification with complex multimodal fusion, yet lacking explicit sentiment explainability. In this paper, we reformulate MABSA as a generative and explainable task, proposing a unified framework that simultaneously predicts aspect-level sentiment and generates natural language explanations. Based on multimodal large language models (MLLMs), our approach employs a prompt-based generative paradigm, jointly producing sentiment and explanation. To further enhance aspect-oriented reasoning capabilities, we propose a dependency-syntax-guided sentiment cue strategy. This strategy prunes and textualizes the aspect-centered dependency syntax tree, guiding the model to distinguish different sentiment aspects and enhancing its explainability. To enable explainability, we use MLLMs to construct new datasets with sentiment explanations to fine-tune. Experiments show that our approach not only achieves consistent gains in sentiment classification accuracy, but also produces faithful, aspect-grounded explanations.
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。