Abstract
Entity-level sentiment classification involves identifying the sentiment polarity linked to specific entities within text. This task poses several challenges: effectively modeling the subtle and complex interactions between entities and their surrounding sentiment expressions; capturing dependencies that may span across sentences; and ensuring consistent sentiment predictions for multiple mentions of the same entity through coreference resolution. Additionally, linguistic phenomena such as negation, ambiguity, and overlapping opinions further complicate the analysis. These complexities make entity-level sentiment classification a difficult problem, especially in real-world, noisy textual data. To address these issues, we propose SpanEIT, a novel framework integrating dynamic span interaction and graph-aware memory mechanisms for enhanced entity-sentiment relational modeling. SpanEIT builds span-based representations for entities and candidate sentiment phrases, employs bidirectional attention for fine-grained interactions, and uses a graph attention network to capture syntactic and co-occurrence relations. A coreference-aware memory module ensures entity-level consistency across documents. Experiments on FSAD, BARU, and IMDB datasets show SpanEIT outperforms state-of-the-art transformer and hybrid baselines in accuracy and F1 scores. Ablation and interpretability analyses validate the effectiveness of our approach, underscoring its potential for fine-grained sentiment analysis in applications like social media monitoring and customer feedback analysis.
Abstract (translated)
实体级别的情感分类涉及识别文本中特定实体所关联的情感极性。这一任务面临几个挑战：有效建模实体与其周围情感表达之间的细微和复杂交互；捕捉可能跨越句子的情感依赖关系；以及通过共指解析确保同一实体的多次提及具有一致的情感预测。此外，语言现象如否定、歧义及重叠意见进一步增加了分析难度。这些复杂性使得实体级别的文本情感分类成为一个难题，特别是在现实世界中的嘈杂文本数据中更为明显。 为了应对这些问题，我们提出了一种名为SpanEIT的新框架，该框架集成了动态跨度互动和图感知内存机制，以增强对实体-情感关系的建模。SpanEIT构建了基于跨度的实体及候选情感短语表示，并采用双向注意力机制来实现细粒度交互，同时使用图形注意力网络捕获句法和共现关系。一个能够识别共指关系的记忆模块确保了文档中同一实体的情感一致性。 在FSAD、BARU和IMDB数据集上的实验表明，SpanEIT在准确率和F1分数上优于现有的变压器和混合基准模型。消融分析及可解释性研究验证了我们方法的有效性，并强调其在社交网络监控与客户反馈分析等应用中进行细粒度情感分析的潜力。
URL
https://arxiv.org/abs/2509.11604
