作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2019, Vol. 45 ›› Issue (4): 169-174,180. doi: 10.19678/j.issn.1000-3428.0050338

• 人工智能及识别技术 • 上一篇    下一篇

基于多样化特征卷积神经网络的情感分析

蔡林森,彭超,陈思远,郭兰英   

  1. 华东师范大学 计算机科学与软件工程学院 上海市高可信计算重点实验室,上海 200062
  • 收稿日期:2018-01-29 出版日期:2019-04-15 发布日期:2019-04-15
  • 作者简介:蔡林森(1992—),男,硕士研究生,主研方向为自然语言处理、情感分析;彭超,副教授、博士;陈思远、郭兰英,硕士研究生。
  • 基金资助:

    国家自然科学基金(61232006);上海市自然科学基金(14ZR1412400)。

Sentiment Analysis Based on Multiple Features Convolutional Neural Networks

CAI Linsen,PENG Chao,CHEN Siyuan,GUO Lanying   

  1. Shanghai Key Laboratory of Trustworthy Computing,School of Computer Science and Software Engineering, East China Normal University,Shanghai 200062,China
  • Received:2018-01-29 Online:2019-04-15 Published:2019-04-15

摘要:

深度网络模型在微博情感倾向性分析过程中难以有效利用情感特征信息,为此,提出一种基于多样化特征信息的卷积神经网络(MF-CNN)模型。结合词语多样化的抽象特征和2种网络输入矩阵计算方法,利用句中的情感信息,以优化情感分类效果。在COAE2014和微博语料数据集上进行文本情感分析,结果表明,MF-CNN模型的情感分类效果优于传统的分类器和深度卷积神经网络模型。

关键词: 情感分析, 深度学习, 情感特征, 卷积神经网络, 自然语言处理

Abstract:

In the task of Micro-Blog sentiment analysis,the deep neural-based models are difficult to make full use of the sentiment information.To solve this problem,a Multiple Features Convolutional Neural Networks(MF-CNN) model is proposed.The emotional information in sentences is effectively utilized by combining the abstract features of words and two kinds of calculation methods of neural model input matrix,and then the sentiment classification result is optimized.The sentiment analysis is carried out on COAE2014 and Micro-Blog text data set,and the results show that the classification effect of MF-CNN model is better than that of traditional classifier and deep Convolutional Neural Network(CNN) model.

Key words: sentiment analysis, deep learning, sentiment feature, Convolutional Neural Network(CNN), natural language processing

中图分类号: