Multi-level graph neural network for text sentiment analysis. (June 2021)

• Record Type: Journal Article
• Authors: Liao, Wenxiong; Zeng, Bi; Liu, Jianqi; Wei, Pengfei; Cheng, Xiaochun; Zhang, Weiwen
• Is Part Of: Computers & electrical engineering. Volume 92(2021)
• Publication Date: 2021-06
• Subjects: text sentiment analysis -- graph neural network -- attention mechanism -- deep learning; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2021.107096
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: The previous graph neural networks used for text sentiment analysis cannot consider both local and global features. A multi-level graph neural network for text sentiment analysis was proposed. Use different edge connection methods and different messaging mechanisms at different levels. Compared with previous methods, our method can better handle text sentiment analysis task. Abstract: Text sentiment analysis is a fundamental task in the field of natural language processing (NLP). Recently, graph neural networks (GNNs) have achieved excellent performance in various NLP tasks. However, a GNN only considers the adjacent words when updating the node representations of the graph, and thus the model can only focus on the local features while ignoring global features. In this paper, we propose a novel multi-level graph neural network (MLGNN) for text sentiment analysis. To consider both local features and global features, we apply node connection windows with different sizes at different levels. Particularly, we integrate a scaled dot-product attention mechanism as a message passing mechanism into our method for fusing the features of each word node in the graph. The experimental results demonstrated that the proposed model outperformed other models in text sentiment analysis tasks. Graphical abstract: The multi-level graph neural network (MLGNN) considers both local features and global features, it applies node connection windows with different sizes and different message passing mechanisms at different levels. The bottom level involves a small connection window, which mainly focuses on the local features; the middle level has a larger connection window, mainly focusing on the long-distance features; the top level fully connects all the word nodes directly, which focuses on the global features. Image, graphical abstract