混合神经网络和条件随机场相结合的文本情感分析

PDF下载HTML

Title:

Text sentiment analysis combining hybrid neural network and conditional random field

作者:

翟学明, 魏巍

华北电力大学 控制与计算机工程学院，河北 保定 071003

Author(s):

ZHAI Xueming, WEI Wei

School of Control and Computer Engineering, North China Electric Power University, Baoding 071003, China

关键词:

卷积神经网络; 门控循环单元; 条件随机场; 文本情感分析; 语言模型; 语义特征; 上下文信息; 分类器

Keywords:

convolutional neural network (CNN); gated recurrent unit (GRU); conditional random field (CRF); text sentiment analysis; language model; semantic feature; contextual information; classifier

分类号:

TP391

DOI:

10.11992/tis.201907041

摘要:

针对当前文本情感分析中神经网络模型训练时间长，上下文信息学习不足的问题，该文提出了一种结合混合神经网络和条件随机场(conditional random fields, CRF)的模型。该模型将神经网络作为语言模型，结合了卷积神经网络(convolutional neural networks, CNN)与双向门控循环单元(bidirectional gated recurrent unit, BiGRU)两种神经网络获得的语义信息和结构特征，采用条件随机场模型作为分类器，计算情感概率分布，进而能够准确地判断情感类别。该文的模型在NLPCC 2014数据集上进行了测试，准确率为91.74%，与其他分类模型相比，可以获得更好的准确性和F值。

Abstract:

To solve problems such as the long training time of neural network models and insufficient contextual-information learning in text sentiment analysis, in this paper, we propose a model that combines a hybrid neural network with the conditional random field (CRF). Taking the neural network as the language model, the model combines the semantic information and structural features of the convolutional neural network with the bi-directional gated recurrent unit. The CRF model is used as a classifier that determines the probability distributions of emotions, from which it can then accurately determine the emotion category. The model was tested on the NLPCC 2014 data set, and achieved an accuracy rate of 91.74%. Compared with other classification models, the proposed model can obtain better accuracy and F values.