基于word embedding和CNN的情感分类模型

尝试将word embedding和卷积神经网络（CNN）相结合来解决情感分类问题。首先，利用Skip-Gram模型训练出数据集中每个词的word embedding，然后将每条样本中出现的word embedding组合为二维特征矩阵作为卷积神经网络的输入；此外，每次迭代训练过程中，输入特征也作为参数进行更新。其次，设计了一种具有3种不同大小卷积核的神经网络结构，从而完成多种局部抽象特征的自动提取过程。与传统机器学习方法相比，所提出的基于word embedding和CNN的情感分类模型成功将分类正确率提升了5.04%。

A sentiment classification model based on word embedding and CNN

This paper tries to propose a method to solve the problem of sentiment classification by integrating word embedding and convolutional neural network (CNN). First of all, a training process accomplished with Skip-gram model has generated word embedding of each word in our dataset. Then, it tried to create a two-dimensional feature matrix which is the combination of word embedding of each word in a training sample as the input of CNN model. Each iteration process of training will also update entries of feature matrix as they are part of model parameters. Secondly, this paper proposes a CNN structure which is mainly composed of three different sizes of convolution kernels so as to complete the automatic extraction process of a variety of local abstract features. Comparing with traditional machine learning algorithms, the proposed word embedding and CNN based sentiment classification model has successfully improved classification accuracy by 5.04%.