J4 ›› 2011, Vol. 38 ›› Issue (3): 181-188.doi: 10.3969/j.issn.1001-2400.2011.03.030

• 研究论文 • 上一篇    下一篇

一种面向观点挖掘的多粒度话题情感联合模型

赵煜;蔡皖东   

  1. (西北工业大学 计算机学院,陕西 西安  710072)
  • 收稿日期:2010-12-27 出版日期:2011-06-20 发布日期:2011-07-14
  • 通讯作者: 赵煜
  • 作者简介:赵煜(1981-),男,西北工业大学博士研究生,E-mail: zhaoyu_mail@126.com.
  • 基金资助:

    国家“863计划”资助项目(2009AA01Z424);西北工业大学基础研究基金资助项目(NPU-FFR-JC200819)

Multi-grain joint model of topic and sentiment for opinion mining

ZHAO Yu;CAI Wandong   

  1. (College of Computer Science, Northwestern Polytechnical Univ., Xi'an   710072, China)
  • Received:2010-12-27 Online:2011-06-20 Published:2011-07-14
  • Contact: ZHAO Yu

摘要:

为了提高文本观点挖掘的效率,通过扩展标准话题模型,提出了一种新颖的多粒度话题情感联合模型(MG-TSJ).模型将文本话题区分为全局和局部两类,同时挖掘文本中涉及的多层次话题信息和情感倾向信息.该模型采用非监督的学习方法,解决了现有方法存在的领域依赖问题.通过在测试语料库上进行实验,该模型在文本情感倾向性分类任务中的准确率达到82.6%,具有和监督分类系统相当的性能| 挖掘话题集合呈现层次化、语义相关的特点,证明了MG-TSJ模型对观点挖掘是可行的和有效的.

关键词: 观点挖掘, 话题模型, 多粒度话题情感联合模型, 非监督学习, 蒙特卡罗模拟法

Abstract:

Based on extensions to standard topic modeling methods,a novel multi-grain joint model of topic and sentiment is proposed to improve efficiency of opinion mining. This model extracts sentiment and hierarchy topic from the text simultaneously, which distinguishes between local topics and global topics. The proposed model adopts the unsupervised learning method to address the issue of being domain dependent in existing methods. According to experiments, this model achieves an accuracy of 82.6% for sentiment classification. It has a performance comparable to that of supervised sentiment classification methods. Moreover, the acquired collection of topics is hierarchy and semantic related. It is proved that the proposed model is feasible and effective for opinion mining.

Key words: opinion mining, topic model, multi-grain joint topic/sentiment model, unsupervised learning, Monte Carlo simulation