基于双注意力卷积神经网络模型的情感分析研究

卷积神经网络（Convolutional Neural Networks，CNN）无法判别输入文本中特征词与情感的相关性.因此提出一种双注意力机制的卷积神经网络模型（Double Attention Convolutional Neural Networks，DACNN），将词特征与词性特征有效融合后得到本文的特征表示，确定情感倾向.本文提出局部注意力的卷积神经网络模型，改进卷积神经网络的特征提取能力，采用双通道的局部注意力卷积神经网络提取文本的词特征和词性特征.然后使用全局注意力为特征分配不同的权重，有选择地进行特征融合，最后得到文本的特征表示.将该模型在MR和SST-1数据集上进行验证，较普通卷积神经网络和传统机器学习方法，在准确率上分别取得0.7%和1%的提升.

Sentiment Classification Based on Double Attention Convolutional Neural Network Model

Convolutional Neural Networks (CNN) cannot discriminate the correlation between feature words and emotions in the input text. Therefore, this paper proposes a double attention mechanism convolutional neural network to incorporate word and POS(Part-of-speech Tagging) information into sentiment classification (Double Attention Convolutional Neural Networks, DACNN), which combines the word features with the part-of-speech features to obtain the feature representation of the text and determine the sentiment tendency. In this paper, we introduce an attention convolutional neural network to incorporate word and POS information into sentiment classification. The first local attention mechanism captures local feature from word and POS channels. And then we propose a novel architect for combining two features by a global attention mechanism, which can decide how much information to use from word or POS information. The model is validated on MR and SST-1 datasets, achieving 0.7% and 1% improvement in accuracy compared to conventional convolutional neural networks and traditional machine learning methods.