图书情报工作 ›› 2017, Vol. 61 ›› Issue (5): 132-140.DOI: 10.13266/j.issn.0252-3116.2017.05.018

• 综述述评 • 上一篇    下一篇

细粒度情感分析研究综述

唐晓波1,2, 刘广超1   

  1. 1. 武汉大学信息管理学院 武汉 430072;
    2. 武汉大学信息资源研究中心 武汉 430072
  • 收稿日期:2016-11-24 修回日期:2017-01-22 出版日期:2017-03-05 发布日期:2017-03-05
  • 通讯作者: 刘广超(ORCID:0000-0001-5561-5887),博士研究生,通讯作者,E-mail::chao1635@126.com
  • 作者简介:唐晓波(ORCID:0000-0001-5885-4509),教授,博士生导师
  • 基金资助:

    本文系国家自然科学基金项目"基于文本和Web语义分析的智能咨询服务研究"(项目编号:71673209)研究成果之一。

Research Review on Fine-grained Sentiment Analysis

Tang Xiaobo1,2, Liu Guangchao1   

  1. 1. School of Information Management, Wuhan University, Wuhan 430072;
    2. Center for the Study of Information Resources, Wuhan University, Wuhan 430072
  • Received:2016-11-24 Revised:2017-01-22 Online:2017-03-05 Published:2017-03-05

摘要:

[目的/意义] 对细粒度情感分析研究进展进行调研和总结,探讨其关键问题、关键技术及未来研究趋势。[方法/过程] 采用文献调研方法,从不同粒度层次的情感分析视角,对粗粒度情感分析到细粒度情感分析的演进过程进行阐述,对细粒度情感分析的实现技术和方法进行归类总结。[结果/结论] 总结细粒度情感分析的两个重要问题:情感词抽取和评价对象属性抽取。本研究有助于了解现阶段细粒度情感分析研究的关键问题及关键方法。

关键词: 细粒度情感分析, 评论对象属性, 情感词, 本体

Abstract:

[Purpose/significance] This paper investigates and summarizes the research progress of fine-grained sentiment analysis, discusses its key issues and key technologies, and points out future research trends. [Method/process] The evolution of coarse-grained sentiment analysis to fine-grained sentiment analysis is described from the perspective of sentiment analysis at different levels of granularity, and the techniques and methods of fine-grained sentiment analysis are classified and summarized using literature research method. [Result/conclusion] This paper summarizes two important issues in fine-grained sentiment analysis, including opinion words extraction and feature extraction. This study will help to understand the key issues and key methods of the fine-grained sentiment analysis.

Key words: fine-grained sentiment analysis, feature, opinion words, ontology

中图分类号: