Enhancing syntactic and semantic features via TextGINConv and Kolmogorov–Arnold networks for aspect-based sentiment analysis

Aspect-based sentiment analysis identifies the sentiment polarity of a given aspect in a sentence. Recent advances have demonstrated the effectiveness of combining syntactic dependency structures with graph convolutional networks. However, traditional graph convolutional networks usually have a simpler message passing mechanism that may describe the relationship between nodes only through the adjacency matrix, often ignoring messages passed by edge features and performing sentiment analysis without considering the specific semantic information of different aspects. In this paper, we innovatively propose a syntactic and semantic enhancement network model for aspect-based sentiment analysis (ESSGKA). To be specific, we combine a self-attention mechanism with an aspect-oriented attention mechanism, enabling the simultaneous learning of aspect-related semantics and the overall semantics of the sentence. TextGINConv focuses more on edge features, which are leveraged to facilitate dense message passing. To enhance the fusion of two distinct feature messages, we propose a novel gated fusion framework based on Kolmogorov–Arnold networks. Extensive experiments on four publicly available datasets show that our model is more competitive than state-of-the-art models.