Abstract
Fine-grained sentiment analysis (FGSA) aims to identify sentiment polarity toward specific aspects within a text, enabling more precise opinion mining in domains such as product reviews and social media. However, traditional FGSA approaches often require task-specific architectures and extensive annotated data, limiting their generalization and scalability. To address these challenges, we propose PL-FGSA, a unified prompt learning-based framework implemented using the MindSpore platform, which integrates prompt design with a lightweight TextCNN backbone. Our method reformulates FGSA as a multi-task prompt-augmented generation problem, jointly tackling aspect extraction, sentiment classification, and causal explanation in a unified paradigm. By leveraging prompt-based guidance, PL-FGSA enhances interpretability and achieves strong performance under both full-data and low-resource conditions. Experiments on three benchmark datasets-SST-2, SemEval-2014 Task 4, and MAMS-demonstrate that our model consistently outperforms traditional fine-tuning methods and achieves F1-scores of 0.922, 0.694, and 0.597, respectively. These results validate the effectiveness of prompt-based generalization and highlight the practical value of PL-FGSA for real-world sentiment analysis tasks.
Abstract (translated)
细粒度情感分析（FGSA）旨在识别文本中针对特定方面的情感极性，从而在产品评论和社会媒体等领域实现更精确的意见挖掘。然而，传统的FGSA方法通常需要特定任务的架构和大量的注释数据，这限制了它们的泛化能力和可扩展性。为了解决这些挑战，我们提出了PL-FGSA，这是一个基于提示学习的统一框架，使用MindSpore平台构建，并结合了轻量级的TextCNN骨干网络。我们的方法将FGSA重新表述为一个多任务提示增强生成问题，在一个统一的范式中同时处理方面提取、情感分类和因果解释。通过利用基于提示的指导，PL-FGSA增强了可解释性，并在全数据集和低资源条件下均表现出色。 我们在三个基准数据集上进行了实验——SST-2、SemEval-2014 Task 4 和 MAMS，结果表明我们的模型始终优于传统的微调方法，并分别取得了F1分数为0.922、0.694 和 0.597 的成绩。这些结果验证了基于提示泛化的有效性，并突显了PL-FGSA在现实世界情感分析任务中的实际价值。
URL
https://arxiv.org/abs/2505.14165
