Evaluation of Logistics Service Quality: Sentiment Analysis of Comment Text Based on Multi-Level Graph Neural Network

Abstract

The world is severely impacted by the coronavirus (COVID19). During the epidemic, logistics service, an often-overlooked pillar of the modern society, steps into the spotlight. However, the service capability is inevitably weakened by the epidemic. The fatigued service providers are increasingly unable to meet the high expectations of users, who therefore leave harsh comments on logistics services. It is important for managers to find information that helps to improve management, out of the biased and angry comments. Text sentiment analysis is a fundamental work in natural language processing (NLP). In recent years, graph neural network (GNN) has achieved excellent performance in various NLP tasks. Nevertheless, GNN only considers the adjacent words, as it updates graph nodes. The model thereby emphasizes local features over global features, and misses the intent of the comment text. This paper constructs a triple graph neural network (TGNN) to serve the sentiment analysis of service texts. Firstly, the corresponding node connection windows were applied on different network layers to consider both local and global features. Next, the graph attention network (GAT) was adopted as the message delivery mechanism to fuse the features of all word nodes in the graph. Experimental results show that, the TGNN can evaluate the comment texts on logistics service quality more accurately than the other models.