Aspect Sentiment Triple Extraction Model Integrating with Syntactic Information

The current mainstream aspect level sentiment analysis methods focus on modeling the relationship between word representations in text and their context, fail to fully utilize the syntactic structure information of the text. This paper proposes a sentiment triplet extraction model IS-ASTE(Integrating with Syntactic information model for Aspect Sentiment Triplet Extraction, IS-ASTE). Firstly, the graph attention layer is employed to obtain contextual context features. Secondly, based on the syntactic dependency tree to obtain the text element's dependency, lexical and distance information, which is combined with the attention mechanism to augment the sentiment representation. Finally, graph convolutional neural networks are integrated to aggregate the feature information of nodes for sentiment classification. The experimental results indicate that, across four representative datasets, the F1 values are all better than those of the baseline model, demonstrating better performance in sentiment analysis.