吉林大学学报(信息科学版) ›› 2019, Vol. 37 ›› Issue (6): 671-676.

• • 上一篇    下一篇

基于回复支持的关键评论提取方法

郭楠1,张勤2a,徐红艳2a,郭舒2b,刘志国3   

  1. 1. 沈阳广播电视大学科研处,沈阳110009; 2. 辽宁大学a. 信息学院; b. 商学院,沈阳110036;3. 中国石油天然气股份有限公司华北化工销售分公司,郑州450000
  • 出版日期:2019-11-24 发布日期:2020-01-06
  • 作者简介:郭楠( 1979— ) ,女,沈阳人,沈阳广播电视大学副教授,硕士,主要从事计算机控制与应用技术研究,( Tel) 86-15640011497( E-mail) 55380833@ qq. com。
  • 基金资助:
    2018 年辽宁省普通高等教育本科教学改革研究基金资助项目( 201804) ; 文化和旅游部基金资助项目( xxhfzzx201804)

Key Comment Extraction Method Based on Reply Support

GUO Nan1,ZHANG Qin2a,XU Hongyan2a,GUO Shu2b,LIU Zhiguo3   

  1. 1. Scientific Research Department,Shenyang Television University,Shenyang 110009,China;2a. College of Information; 2b. Business School,Liaoning University,Shenyang 110036,China;3. North China Chemical Sales Branch,PetroChina Company Limited,Zhengzhou 450000,China
  • Online:2019-11-24 Published:2020-01-06

摘要: 当前网络中充斥着大量的虚假评论,准确识别出代表用户真实感受的关键评论成为评论分析领域研究的热点问题。为此,提出一种基于回复支持的关键评论提取方法,该方法从用户对评论的反馈行为出发,重点考量评论点赞和评论回复两个指标,通过计算评论点赞率和回复率获取评论的回复支持情况,仅对回复支持度高的评论进行提取,从而剔除了大量虚假或无用的评论,提升了关键评论提取的准确性。最后,通过与现有主流方法进行实验对比,验证了该方法具有较高的正确率和召回率。

关键词: 在线评论, 回复支持, 关键句提取, 潜在狄利克雷分布

Abstract: Online comment is an effective way for users to express their opinions or suggestions on commodities.Analysis of comments is the basis of developing personalized services and improving the performance of commodities. However,there are a lot of false comments in the network. Accurate identification of the key comments which represent users' real feelings has become a hot issue in the field of comment analysis. A key comment extraction method based on reply support was proposed. The proposed method starts from user's feedback behavior to comments,and focuses on two indicators: like comment and comment reply. By calculating the like comment rate and comment reply rate,the method obtains the comment's reply support,only extracts the comment with high reply support,thus eliminating a large number of false or useless comments,and improves the accuracy of key comment extraction. Finally,through the experimental comparison with the existing mainstream methods,it is verified that the proposed method has a high accuracy and recall rate.

Key words: online comment, reply support, key sentences extraction, latent Dirichlet allocation ( LDA)

中图分类号: 

  • TP391