An aspect sentiment classification model for graph attention networks incorporating syntactic, semantic, and knowledge

Aspect sentiment classification tasks aim to identify the aspect in a sentence and express the sentiment polarities of the aspect. In existing studies, combining different deep learning models has achieved good results in aspectual sentiment classification tasks; however, problems such as complex syntactic parsing relationships, insensitivity to syntactic structure information and lack of exploitation of external sentiment knowledge. We propose a graph attention network (SSK-GAT) model incorporating syntactic, semantic and knowledge that considers reshaped syntactic dependencies, multi-head selfattention to capture semantic information of context and introduction of an emotion knowledge base to enhance aspect-related emotional information. In previous studies, aspect and context were modeled separately. Hence, to enhance the representation of sentiment between the aspect and contexts, we use the interactive modeling of aspect and context at the output layer to obtain deeper information through mutual learning. Our SSK-GAT model improved on three publicly available datasets compared to the baseline approaches.