Sentiment Domain Adaptation with Multi-Level Contextual Sentiment Knowledge
ACM International Conference on Information and Knowledge Management(2016)
摘要
Sentiment domain adaptation is widely studied to tackle the domain-dependence problem in sentiment analysis field. Existing domain adaptation methods usually train a sentiment classifier in a source domain and adapt it to the target domain using transfer learning techniques. However, when the distributions of sentiment expressions between the source and target domains are significantly different, the adaptation performance will heavily decline. In this paper, we propose a new sentiment domain adaptation approach by adapting the sentiment knowledge in general-purpose sentiment lexicons to a specific domain. Since the general sentiment words in general-purpose sentiment lexicons convey consistent sentiments in different domains, they usually have better generalization performance than a sentiment classifier trained in a source domain. In addition, we propose to extract various kinds of contextual sentiment knowledge from the massive unlabeled samples in target domain and formulate them as sentiment relations among the sentiment expressions. It can help propagate the sentiment knowledge in general sentiment words to massive domain-specific sentiment expressions. Besides, we propose a unified framework to incorporate these different kinds of sentiment knowledge and learn a domain-specific sentiment classifier for target domain. Moreover, we propose an efficient optimization algorithm to solve the model of our approach. Extensive experiments on benchmark datasets validate the effectiveness and efficiency of our approach.
更多查看译文
关键词
sentiment classification,domain adaptation,contextual knowledge
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络