计算机与现代化 ›› 2022, Vol. 0 ›› Issue (05): 33-39.

• 算法设计与分析 • 上一篇    下一篇

一种基于图卷积神经网络和依存分析的财经新闻情感分析方法

  

  1. (1.中国电子科技集团第三十研究所,四川成都610041;2.成都信息工程大学计算机学院,四川成都610225)
  • 出版日期:2022-06-08 发布日期:2022-06-08
  • 作者简介:姚春华(1974—),男,四川乐至人,高级工程师,本科,研究方向:网络空间安全,E-mail: bingmeng744211@qq.com; 张学磊(1997—),男,四川巴中人,硕士研究生,研究方向:自然语言处理,情感分析,E-mail: zhangxueleie@163.com; 宋馨宇(1994—),男,黑龙江齐齐哈尔人,硕士研究生,研究方向:自然语言处理,情感分析,E-mail: xinyu.s@foxmail.com; 张举(1998—),男,四川资阳人,硕士研究生,研究方向:自然语言处理,E-mail: 461009747@qq.com; 蔡佳志(1998—),男,四川达州人,硕士研究生,研究方向:自然语言处理,E-mail: 113687914@qq.com; 冯翱(1979—),男,四川岳池人,副教授,研究方向:自然语言处理,数据挖掘,E-mail: fengao@cuit.edu.cn。
  • 基金资助:
    国家重点研发计划项目(2017YFC0820700); 四川省重点研发项目(2020YFG0168); 四川省属高校科研创新团队项目(18TD0026)

A Financial News Sentiment Analysis Method Based on Graph Convolutional Neural Network and Dependency Analysis

  1. (1. The 30th Research Institute of China Electronics Technology Group Corporation, Chengdu 610041, China;
    2. College of Computer, Chengdu University of Information Technology, Chengdu 610225, China)
  • Online:2022-06-08 Published:2022-06-08

摘要: 财经新闻的情感分析有助于企业和投资者确定投资风险和提高经济效益,具有较高的应用价值。针对财经新闻文本,提出一种在图卷积神经网络中使用依存句法分析(Dependency Analysis-based Graph Convolutional Network, DA-GCN)的情感分析方法。该方法通过分析文档中词语的依存关系,获取句子的语序信息和文档中重要的句子成分,再通过词语在文档中的共现信息实现信息传递和对图的参数更新。在财经新闻数据集上进行的实验表明,本文提出的方法与传统深度学习方法相比,在各项评价指标上都取得显著提升。

关键词: 图神经网络, 财经新闻, 依存分析, 情感分析, 深度学习

Abstract: Sentiment analysis of financial news helps enterprises and investors to determine investment risks and improves economic benefits, resulting in high application value. Graph neural networks have excellent performance in text classification, and have been applied to the field of sentiment analysis. In this paper, we propose a sentiment analysis method that uses dependency syntax analysis in graph convolutional neural networks (Dependency Analysis-based Graph Convolutional Network, DA-GCN) for financial news. This method obtains the word order information of the sentence and the syntactic in the document by analyzing the dependency of words in the document. It then implements information propagation and weight updates in the graph with co-occurrence information in each document. Experiments on a financial news dataset show that our model achieves significant performance improvements over traditional deep learning methods.

Key words: graph neural networks, financial news, dependency analysis, sentiment analysis, deep learning