• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>SLSP 2013 >A.-H. Dediu et al. (Eds.): SLSP 2013, LNAI 7978, pp. 284-296, 2013. ? Springer-Verlag Berlin Heidelberg 2013 Factored Semantic Sequence Kernel for Sentiment Polarity Classification
【24h】

A.-H. Dediu et al. (Eds.): SLSP 2013, LNAI 7978, pp. 284-296, 2013. ? Springer-Verlag Berlin Heidelberg 2013 Factored Semantic Sequence Kernel for Sentiment Polarity Classification

机译：啊。 dediu等。 （EDS。）：SLSP 2013，LNAi 7978，PP。284-296,2013。 Springer-Verlag Berlin Heidelberg 2013因素语义序列核心为情感极性分类

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Sentiment analysis is an area of research that has gained considerable attention in recent years due to the increasing availability of opinionated information online. The majority of the work in sentiment analysis considers the polarity of word terms rather than the polarity of specific senses of the word but different senses of a word can have different opinion-related properties. In order to address this issue we consider novel semantic features of words in the context of a sentence. We take a sentence as a sequence of words augmented with features based on word sense disambiguation and sentiment lexicons with sense specific opinion-related properties. We then use a factored version of the sequence kernel in a support vector machine, and apply it to sentiment classification of sentences. We evaluate this sentiment analysis methodology on three publicly available corpuses. We also evaluate the effectiveness of several publicly available sense specific polarity lexicons and combinations. Experiments show that our factored approach offers improvements over the surface words baseline and other state-of-the-art kernels.
机译：情感分析是由于在线提供了各种信息的可用性，近年来近年来取得了相当大的关注。情绪分析中的大多数工作都考虑了单词术语的极性，而不是单词的特定感官的极性，但是单词的不同感官可以具有不同的意见相关的属性。为了解决这个问题，我们考虑在句子的上下文中的单词的新颖语义特征。我们将一个句子作为一系列单词，基于词义歧义消歧和情绪词汇的特征增强，具有感知特定的意见相关性。然后，我们在支持向量机中使用序列内核的常规版本，并将其应用于句子的情绪分类。我们评估了三种公开的核肉的这种情绪分析方法。我们还评估了几种公开可用的特定极性词汇和组合的有效性。实验表明，我们的辅导方法提供了对地表词基线和其他最先进的内核的改进。

著录项

相似文献

  • 外文文献
  • 中文文献
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号