Word polarity attention in sentiment analysis
Word polarity attention in sentiment analysis
复制标题
DOI：
10.1007/s10015-018-0439-9
复制
发表时间：
2018-06
影响因子：
0.9
通讯作者：
Yohei Hiyama;H. Yanagimoto
中科院分区：
文献类型：
--
作者：
Yohei Hiyama;H. Yanagimoto
神经网络方法是端到端的学习方法，没有精心设计的训练数据，并在情感分析中实现高性能。由于神经网络的体系结构复杂，很难分析它们的工作方式并找到瓶颈来提高其性能。为了解决这个问题，我们提出了带有注意机制的神经情感分析。利用注意机制，我们可以找到重要的词来确定句子的情感极性。此外，我们可以理解为什么情感分析不能正确分类情感极性。我们比较了我们的方法与神经情感分析没有注意机制TSUKUBA语料库和斯坦福大学情感树库（SST）。实验结果表明，该方法具有较好的可解释性，并能达到较高的精度。
Neural network approaches are end-to-end learning approaches without well-designed training data and achieve high performance in sentiment analysis. Because of complex architecture of a neural network, it is difficult to analyze how they work and find their bottleneck to improve their performance. To remedy it, we propose neural sentiment analysis with attention mechanism. Using attention mechanism, we can find important words to determine sentiment polarity of a sentence. Moreover, we can understand why the sentiment analysis could not classify sentiment polarity correctly. We compare our method with neural sentiment analysis without attention mechanism over TSUKUBA corpus and Stanford Sentiment Treebank (SST). Experimental results show that our method is interpretable and can achieve higher precision.