GP-GCN: Global features of orthogonal projection and local dependency fused graph convolutional networks for aspect-level sentiment classification

Aspect-level sentiment classification, a significant task of fine-grained sentiment analysis, aims to identify the sentimental information expressed in each aspect of a given sentence The existing methods combine global features and local structures to obtain good classification results. However, the introduction of global features will bring noise and reduce the classification accuracy. To solve this problem, a new method is proposed, named GP-GCN. In our proposed method, the global feature is further simplified to reduce the noise . The local structures and global features obtained by orthogonal feature projection are introduced into aspect-level sentiment classification. First, the simplified global feature structures of text are built. Through orthogonal projection, GCN not only weakens the dependency of the graph node in updating process but also reduces the dependency between node and corpus. Next, syntactic dependency structure and sentence sequence information are utilised to mine the local dependency structure of sentences. A percentage-based multi-headed attention mechanism is proposed to measure the critical output of GCN, which can better represent sentences for given aspects. Finally, location coding is input to simulate aspect-specific representations between each aspect and its context such that the text becomes more discriminative in sentiment classification. The experimental results show that the proposed method effectively improves the accuracy of text sentiment classification.