学会官网  |  加入学会  |  登录学会  |  English 

电子学报 ›› 2015, Vol. 43 ›› Issue (12): 2530-2535.DOI: 10.3969/j.issn.0372-2112.2015.12.028

• 科研通信 • 上一篇    下一篇

在线评论情感计算与博弈预测

卜湛1, 伍之昂1, 曹杰1, 朱桂祥2   

  1. 1. 南京财经大学江苏省电子商务重点实验室, 江苏南京 210003;
    2. 南京理工大学计算机科学与技术学院, 江苏南京 210094
  • 收稿日期:2014-10-15 修回日期:2015-01-09 出版日期:2015-12-25
    • 通讯作者:
    • 伍之昂
    • 作者简介:
    • 卜湛 男,1987年6月出生,安徽铜陵人.2009年和2014年分别在西安科技大学和南京航空航天大学获工学学士和工学博士学位.现为南京财经大学江苏省电子商务重点实验室讲师,主要研究领域为社会网络计算、web挖掘.E-mail:buzhan@nuaa.edu.cn
    • 基金资助:

    • 国家自然科学基金 (No.71372188); 国家级电子商务信息处理国际联合中心 (No.2013B01035); 国家科技支撑计划 (No.2013BAH16F01); 江苏省科技支撑计划工业部分 (No.BE2014141,No.BE2012185); 江苏省高校自然科学研究项目 (No.12KJA520001,No.14KJA520001,No.14KJB520015); 江苏高校优势学科建设工程资助项目

Affective Computing and Game Theory Based Prediction for Online Reviews

BU Zhan1, WU Zhi-ang1, CAO Jie1, ZHU Gui-xiang2   

  1. 1. Jiangsu Provincial Key Laboratory of E-Business, Nanjing University of Finance and Economics, Nanjing, Jiangsu 210003, China;
    2. College of Computer Science and Technology, Nanjing University of Science and Technology, Nanjing, Jiangsu 210094, China
  • Received:2014-10-15 Revised:2015-01-09 Online:2015-12-25 Published:2015-12-25
    • Supported by:
    • National Natural Science Foundation of China (No.71372188); National International Joint Research Center for E-commerce Information Processing (No.2013B01035); National Key Technology Research and Development Program of the Ministry of Science and Technology (No.2013BAH16F01); Industry Project of Science and Technology Support Project of Jiangsu Province (No.BE2014141, No.BE2012185); Natural Science Research Program of Universities in Jiangsu Province (No.12KJA520001, No.14KJA520001, No.14KJB520015); A Project Funded by the Priority Academic Program Development of Jiangsu Higher Education Institutions

PDF

摘要：

传统的情感分析研究大多立足于解决主观性文本的情感分类问题,面向复杂交互式文本的情感演化分析却力所不逮.本文以天涯论坛短文本中文在线评论为研究对象,首先提出一种高效的情感计算框架捕捉在线评论所蕴含的情感倾向;然后将情感计算和博弈论相结合提出情感演化预测算法,以混合纳什均衡策略作为交互行为的预测结果;最后在大规模评论数据集上,验证了情感计算框架的有效性和情感演化预测算法的准确性.

关键词: 情感分析, 在线评论, 情感计算, 博弈论, 情感演化

Abstract:

Most of the existing sentiment analysis was performed in the sentiment classification for subjective texts;the emotional evolution analysis for complex interactive texts was not yet thoroughly targeted by the research community.This paper is concerned on short-text Chinese online reviews collected from Tianya forum.Firstly,an efficient affective computing framework is proposed to capture the underlying emotions of online reviews.Secondly,a game theory based emotional evolution prediction algorithm combining the affective computing is proposed,in which the mixed Nash Equilibrium strategies are calculated as the future emotional behavior of interactive users.Experimental results on the large-scaled review dataset are provided to demonstrate the effectiveness and accurateness of our approaches.

Key words: sentiment analysis, online reviews, affective computing, game theory, emotional evolution

中图分类号: 

京ICP备12041980号-1　版权所有 ©《电子学报》编辑部