Sentiment Classification with Gated CNN for Customer Reviews
Sentiment Classification with Gated CNN for Customer Reviews
复制标题
DOI：
10.1109/isai-nlp.2018.8692959
复制
发表时间：
2018-11
期刊：
影响因子：
--
通讯作者：
M. Okada;H. Yanagimoto;Kiyota Hashimoto
中科院分区：
文献类型：
--
作者：
M. Okada;H. Yanagimoto;Kiyota Hashimoto
递归神经网络（RNN）已被应用于情感分类，但RNN通常比卷积神经网络（CNN）更重，因此人们对CNN应用于语言任务的兴趣更大。在本文中，我们提出了一种将门控CNN（gCNN）与Maxpooling应用于客户评论情感分类的方法。在我们的提案中，gCNN的应用是情感分类，而不是构建语言模型。我们的实验是用亚马逊产品评论数据集和TripAdvisor的日本评论数据集进行的。每个评论的整体都被用作输入，而不是每个句子。结果是，gCNN在情感分类中的简单应用在两个数据集上实现了足够的准确性。因此，这意味着gCNN被证明可以很好地进行情感分类，比RNN快得多，在不同的语言数据集上都有很好的结果。
Recurrent neural networks(RNNs) have been applied to sentiment classification but RNNs is usually heavier than convolutional neural networks (CNNs), turning more interest in the application of CNNs to language tasks. In this paper we propose a method to apply gated CNN (gCNN) with Maxpooling to sentiment classification of customer reviews. In our proposal, the application of gCNN is to sentiment classification, instead of constructing a language model. Our experiment is conducted with Amazon Product Review dataset and Japanese review dataset of TripAdvisor. The whole of each review is used as an input, instead of each sentence. The result is that a simple application of gCNN to sentiment classification achieved sufficient accuracies with the two datasets. Thus, an implication is that gCNN is proven to work fine for sentiment classification much faster than RNNs with fine results in the different language datasets.