Joint Aspect-Sentiment Analysis with Minimal User Guidance
Joint Aspect-Sentiment Analysis with Minimal User Guidance
复制标题
DOI：
10.1145/3397271.3401179
复制
发表时间：
2020-07
期刊：
影响因子：
--
通讯作者：
Honglei Zhuang;Fang Guo;Chao Zhang-;Liyuan Liu;Jiawei Han
中科院分区：
文献类型：
--
作者：
Honglei Zhuang;Fang Guo;Chao Zhang-;Liyuan Liu;Jiawei Han
基于文本的情感分析是文本理解的重要一步，它使许多应用程序受益。由于大多数现有的算法需要大量的标记数据或大量的外部语言资源，将它们应用于新的领域或新的语言通常是昂贵和耗时的。我们的目标是从一个未标记的语料库中建立一个基于方面的情感分析模型，其中用户的指导最少，即，对于每个方面类和每个情感类，只有一小组种子词。我们采用了一个自动编码器结构，注意学习两个字典矩阵的方面和情绪分别作为一个方面或情绪类的嵌入向量的字典的每一行。我们建议利用用户给定的种子词来正则化字典学习。此外，我们通过加入方面和情感编码器来重建句子中的情感来改进模型。联合结构使得词典中的情感嵌入能够针对每个方面的特定于方面的情感词进行调整，这有利于分类性能。我们在两个真实的数据集上进行了实验，以验证我们的模型的有效性。
Aspect-based sentiment analysis is a substantial step towards text understanding which benefits numerous applications. Since most existing algorithms require a large amount of labeled data or substantial external language resources, applying them on a new domain or a new language is usually expensive and time-consuming. We aim to build an aspect-based sentiment analysis model from an unlabeled corpus with minimal guidance from users, i.e., only a small set of seed words for each aspect class and each sentiment class. We employ an autoencoder structure with attention to learn two dictionary matrices for aspect and sentiment respectively where each row of the dictionary serves as an embedding vector for an aspect or a sentiment class. We propose to utilize the user-given seed words to regularize the dictionary learning. In addition, we improve the model by joining the aspect and sentiment encoder in the reconstruction of sentiment in sentences. The joint structure enables sentiment embeddings in the dictionary to be tuned towards the aspect-specific sentiment words for each aspect, which benefits the classification performance. We conduct experiments on two real data sets to verify the effectiveness of our models.