Graph Attention Network with Dependency Syntax for Aspect level Sentiment Analysis

• 1、Chongqing University of Posts and Telecommunications College of Computer Science and Technology， Chongqing 400000

Abstract：The purpose of aspect level sentiment analysis is to judge the sentiment polarity of words or phrases with subjective emotions in a sentence. The existing mainstram method is to extract the context semantics of aspect targets words based on attention mechanism, but the attention mechanism is not sensitive to location information and is not good at capturing long-distance syntactic dependency information. To solve the existing problems, this paper proposes an aspect specific graph attention network model to make up for the shortcoming of attention mechanism. Firstly, the dependency syntax tree of a sentence is obtained by dependency parsing, and then the adjacency matrix with local location information is generated by combining the local location relationship of aspect target words in the context. Then the context semantics of aspect target words is extracted by multi-layer graph attention network, which makes the semantic features of extracted aspect targets more abundant. The model can better capture the long-distance syntactic dependency and also capture the local information of aspect words. The model has achieved better results on five benchmark data sets. The effectiveness of the model is verified by model comparision and experimental analysis.

Keywords： Natural language processing Aspect level sentiment analysis Graph attention network Dependency parsing