融合时间序列与多尺度特征的虚假评论识别方法

doi:10.19678/j.issn.1000-3428.0050754

计算机工程 ›› 2019, Vol. 45 ›› Issue (3): 278-285,292. doi: 10.19678/j.issn.1000-3428.0050754

融合时间序列与多尺度特征的虚假评论识别方法

狄瑞彤^1a,2,王红^1a,1b,2,房有丽^1a,2

1.山东师范大学 a.信息科学与工程学院;b.生命科学学院,济南 250358; 2.山东省分布式计算机软件新技术重点实验室,济南 250014

收稿日期:2018-03-13 出版日期:2019-03-15 发布日期:2019-03-15
作者简介:狄瑞彤(1993—),女,硕士研究生,主研方向为数据挖掘、机器学习;王红(通信作者),教授、博士;房有丽,硕士研究生。
基金资助:
国家自然科学基金(61672329,61373149);山东省教育科学规划项目(ZK1437B010)。

Fake Reviews Identification Method Fusing Time Series and Multi-scale Features

DI Ruitong^1a,2,WANG Hong^1a,1b,2,FANG Youli^1a,2

1a.School of Information Science and Engineering; 1b.College of Life Science,Shandong Normal University,Jinan 250358,China; 2.Shandong Provincial Key Laboratory of Distributed Computer Software Novel Technology,Jinan 250014,China

Received:2018-03-13 Online:2019-03-15 Published:2019-03-15

摘要/Abstract

摘要：

结合时间序列与多尺度特征,提出一种改进的虚假评论识别方法。考虑时间因素对评分及其分布的影响,构建基于多维时间序列的虚假评论识别模型提取异常评论特征,并对异常评论特征进行层次划分,根据多尺度特征思想获取基准尺度特征及细分尺度特征。采用基于密度峰值的聚类算法识别虚假评论,并提高虚假评论识别模型的抗噪能力。实验结果表明,与基于基准尺度特征和多尺度特征的密度峰值聚类虚假评论识别方法相比,该方法的AUC值达到92%,虚假评论识别正确率更高。

关键词: 虚假评论, 时间序列, 多尺度, 主成分分析, 聚类

Abstract:

This paper proposes an improved fake reviews identification method combining time series with multi-scale features.Considering the influence of time factors on the ratings and its distribution,it constructs fake reviews identification model based on multi-dimensional time series to extract abnormal features.It divides abnormal review features into groups,benchmark features and subdivision scale features are extracted according to multi-scale feature idea.To improve the noise immunity of false reviews identification models,it uses a clustering algorithm based on density peaks to identify fake views.Experimental results show that this method has higher identification correct rate of fake reviews and AUC value reach 92% compared with false comment identification method through density peaks clustering based on benchmark scale feature and multi-scale feature.

Key words: fake review, time series, multi-scale, Principal Component Analysis(PCA), clustering

中图分类号:

TP311

狄瑞彤,王红,房有丽. 融合时间序列与多尺度特征的虚假评论识别方法[J]. 计算机工程, 2019, 45(3): 278-285,292.

DI Ruitong,WANG Hong,FANG Youli. Fake Reviews Identification Method Fusing Time Series and Multi-scale Features[J]. Computer Engineering, 2019, 45(3): 278-285,292.

http://www.ecice06.com/CN/Y2019/V45/I3/278

参考文献

［1］ALSPECTOR J.SVM-based filtering of E-mail spam with content-specific misclassification costs［C］//Proceedings of Workshop on Text Mining.Washington D.C.,USA:IEEE Press,2001:1-6.
［2］BECCHETTI L,CASTILLO C.Link-based characterization and detection of Web spam［C］//Proceedings of the 2nd International Workshop on Adversarial Information Retrieval on the Web.Washington D.C.,USA:IEEE Press,2006:1-8.
［3］JINDAL N,LIU B.Opinion spam and analysis［C］//Proceedings of International Conference on Web Search and Data Mining.New York,USA:ACM Press,2008:219-230.
［4］OTT M,CHOI Y,CARDIE C,et al.Finding deceptive opinion spam by any stretch of the imagination［C］//Proceedings of Meeting of the Association for Computational Linguistics:Human Language Technologies.Cambridge,USA:Association for Computational Linguistics,2011:309-319.
［5］宋海霞,严馨,余正涛,等.基于自适应聚类的虚假评论检测［J］.南京大学学报(自然科学版),2013,49(4):433-438.
［6］CHANG T,PING Y H,MINGS C,et al.Detecting fake review with rumor model—case study in hotel review［C］//Proceedings of International Conference on Intelligent Science and Big Data Engineering.Berlin,Germany:Springer,2015:181-192.
［7］LI J,OTT M,CARDIE C,et al.Towards a general rule for identifying deceptive opinion spam［C］//Proceedings of Meeting of the Association for Computational Linguistics.Cambridge,USA:Association for Computational Linguistics,2014:1566-1576.
［8］DEWANG R K,SINGH A K.Identification of fake reviews using new set of lexical and syntactic features［C］//Proceedings of the 6th International Conference on Computer and Communication Technology.New York,USA:ACM Press,2015:115-119.
［9］LI H,LIU B,MUKHERJEE A,et al.Spotting fake reviews using positive-unlabeled learning［J］.Computacion Y Sistemas,2014,18(3):467-475.
［10］GAO J,DONG Y W,SHANG M,et al.Group-based ranking method for online rating systems with spamming attacks［EB/OL］.［2018-02-11］.https://arxiv.org/abs/1501.00677.
［11］HUSNA H,PHITHAKKITNUKOON S,PALLA S,et al.Behavior analysis of spam botnets［C］//Proceedings of the 3rd International Conference on Communication Systems Software and Middleware and Workshops.Washington D.C.,USA:IEEE Press,2008:6-10.
［12］HAYATI P,CHAI K,POTDAR V,et al.Behaviour-based Web spambot detection by utilising action time and action frequency［C］//Proceedings of ICCSA’10.Berlin,Germany:Springer,2010:351-360.
［13］XIE S,WANG G,LIN S,et al.Review spam detection via time series pattern discovery［C］//Proceedings of the 21st International Conference Companion on World Wide Web.New York,USA:ACM Press,2012:635-636.
［14］柳萌萌,张书良,韩玉辉,等.多尺度数据挖掘方法［J］.软件学报,2016,27(12):3030-3050.
［15］LAPPAS T.Fake reviews:the malicious perspective［C］//Proceedings of International Conference on Applications of Natural Language Processing and Information Systems.Berlin,Germany:Springer,2012:23-34.
［16］REN Y F,YIN L,JI D H.Deceptive reviews detection based on Language steucture and sentiment polrit［J］.Journal of Frontiers of Computer Science and Technology,2014,8(3):313-320.
［17］BREIMAN L.Random forest［J］.Machine Learning,2001,45(1):5-32.
［18］张希翔,赵欢.基于随机森林的语音人格预测方法［J］.计算机工程,2017,43(6):253-258.
［19］周文谊,王吉源.一种模糊森林学习方法及其行人检测应用［J］.计算机工程,2017,43(3):304-308.
［20］RODRIGUEZ A,LAIO A.Clustering by fast search and find of density peaks［J］.Science,2014,344(6191):1492.
［21］刘曾超前,许光銮.基于密度峰值的轨迹聚类算法［J］.国外电子测量技术,2017,36(4):59-65.
［22］邵珠峰,姬东鸿.基于情感特征和用户关系的虚假评论者的识别［J］.计算机应用与软件,2016,33(5):158-161.

[1]	江雨燕, 陶承凤, 李平. 数据增强和自适应自步学习的深度子空间聚类算法[J]. 计算机工程, 2023, 49(8): 96-103, 110.
[2]	宋志娜, 李莎, 杨建明, 徐川. 基于特征与区域定位增强的遥感舰船目标检测[J]. 计算机工程, 2023, 49(8): 257-264.
[3]	郑美光, 杨泳. 基于互信息软聚类的个性化联邦学习算法[J]. 计算机工程, 2023, 49(8): 20-28.
[4]	李泽水, 冀俊忠, 杨翠翠. 基于边权重信息深度网络嵌入的PPIN功能模块检测[J]. 计算机工程, 2023, 49(8): 69-76.
[5]	邱天晨, 郑小盈, 祝永新, 封松林. 面向非独立同分布数据的联邦学习架构[J]. 计算机工程, 2023, 49(7): 110-117.
[6]	汤卫芬, 高翠芳. 极值点自适应加权的动态时间规整算法[J]. 计算机工程, 2023, 49(7): 150-160.
[7]	王款, 宣士斌, 何雪东, 李紫薇, 李嘉祥. 基于交叉注意力Transformer的人体姿态估计方法[J]. 计算机工程, 2023, 49(7): 223-231.
[8]	熊中敏, 曾旗, 卢鹏, 王振华, 郑宗生. 基于残差注意力多尺度关系网络的逻辑推理[J]. 计算机工程, 2023, 49(6): 227-233,241.
[9]	高小方, 原玉梁, 温静, 白雪飞. 面向相交多流形聚类的标签传播算法[J]. 计算机工程, 2023, 49(6): 90-98.
[10]	位雅, 张正军, 何凯琳, 唐莉. 基于相对密度的密度峰值聚类算法[J]. 计算机工程, 2023, 49(6): 53-61.
[11]	戴浩磊, 黄永慧, 周郭许. 基于超图正则化非负张量链分解的聚类分析[J]. 计算机工程, 2023, 49(6): 81-89.
[12]	焦义, 徐华兴, 毛晓波, 李楠, 姚国梁, 倪金红, 徐向阳. 融合多尺度特征的脑电情感识别研究[J]. 计算机工程, 2023, 49(5): 81-89,96.
[13]	丁子轩, 俞雷, 张娟, 李想, 王新宇. 基于深度残差自适应注意力网络的图像超分辨率重建[J]. 计算机工程, 2023, 49(5): 231-238.
[14]	李晓腾, 张盼盼, 勾智楠, 高凯. 基于多任务学习的多模态命名实体识别方法[J]. 计算机工程, 2023, 49(4): 114-119.
[15]	程小辉, 李钰, 康燕萍. 基于中间图特征提取的卷积网络双标准剪枝[J]. 计算机工程, 2023, 49(3): 105-112.

选择文件类型/文献管理软件名称

选择包含的内容

融合时间序列与多尺度特征的虚假评论识别方法

Fake Reviews Identification Method Fusing Time Series and Multi-scale Features

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

融合时间序列与多尺度特征的虚假评论识别方法

Fake Reviews Identification Method Fusing Time Series and Multi-scale Features

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价