Please wait a minute...
Data Analysis and Knowledge Discovery  2019, Vol. 3 Issue (9): 1-15    DOI: 10.11925/infotech.2096-3467.2018.0959
Current Issue | Archive | Adv Search |
Detecting Product Review Spam: A Survey
Jiafen Wu,Feicheng Ma()
Center for Studies of Information Resources, Wuhan University, Wuhan 430072, China
Download: PDF(706 KB)   HTML ( 41 ) 
Export: BibTeX | EndNote (RIS)      
Abstract  

[Objective] This paper reviews current studies on fighting product review spam. [Coverage] We searched “review spam” with eight major scholarly databases (e.g., WoS, CNKI and EI, etc.), and retrieved a total of 90 relevant papers. [Methods] First, we adopted systematic review procedure to identify and categorize the methods detecting product review spam. Then, we compared the impacts of spam features on detection performance. [Results] The spam features and detection methods were the key issues in fighting product review spam. The acquisition of large-scale annotation data was a challenging task for current research. [Limitations] We did not examine the detection and classification methods for spammers. [Conclusions] This paper analyzes spam detection methods from the perspectives of data acquisition, spamming features and detection methods. It offers suggestions and directions for future research.
Key words： Review Spam Detection      Review Spam      Spamming Features      Detection Methods     
Received: 31 August 2018      Published: 23 October 2019
:  TP391  
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Jiafen Wu
Feicheng Ma

Cite this article:

Jiafen Wu,Feicheng Ma. Detecting Product Review Spam: A Survey. Data Analysis and Knowledge Discovery, 2019, 3(9): 1-15.

URL:

http://manu44.magtech.com.cn/Jwk_infotech_wk3/EN/10.11925/infotech.2096-3467.2018.0959     OR     http://manu44.magtech.com.cn/Jwk_infotech_wk3/EN/Y2019/V3/I9/1

序号 质量标准 判断方法 排除文献数
1 不是以产品虚假评论识别方法为研究主题的文献(例如: 社交媒体虚假评论、评论质量、评论效用、治理研究等) 阅读文献标题、摘要及关键字 54
2 没有提出完整识别方法、没有指明实验数据集、没有进行实证研究的文献(缺少以上内容无法进行特征、方法性能的对比) 精读文献 6
3 冗余文献(相同作者的研究发表在不同会议或期刊上, 选择其中最新最全的版本) 精读文献 10
总计 70
特征类型 特征 特征功能 提取方法
语言特征 词袋/n-grams 以向量形式表示文本, 计算评论文本的相似度 词法分析, 建立词袋模型或n-grams模型, 常用的有Unigram、Bigrams及Trigrams
词性(Part-of-Speech, POS) 捕捉真实和虚假评论的词性分布差异 词法分析, 进行词性标注及词频统计
LIWC 从语言学和心理学角度理解虚假评论文本 词法分析, 使用LIWC③(Linguistic Inquiry and Word Count)工具的输出结果
句法结构 获取评论文本深层的句法结构特点 句法分析, 使用概率上下文无关文法(Probabilistic Context-Free Grammar, PCFG)或依存关系分析树
情感 捕捉虚假评论的极端情感倾向 语义分析, 情感分析
文本特征 文本表示 获取评论深层语义表示 语义分析, 通过建立词嵌入模型、深度学习模型进行文本表示
文体风格 获取评论者写作风格特点 词法和句法分析, 基于词汇和句法特征分析提取
元数据 从评论语言以外的角度获取评论、评论者
及评论对象的属性		 基于评论正文以外的其他与评论相关的数据提取, 例如评论长度、评论时间、评分、评论ID、产品ID等
虚假行为 行为说明 虚假行为特征 量化方法 特征说明
复制评论
行为		 为降低写虚假评论的时间代价, 虚假评论者倾向于复制自己或他人的评论, 致使评论内容的相似程度较高[14,15]。 最大内容相似度[16]
(Maximum Content
Similarity, MCS)		 ${{f}_{MCS}}={{\max }_{{{r}_{i}},{{r}_{j}}\in {{R}_{a}},i<j}}\cos ({{r}_{i}},{{r}_{j}})$ 利用余弦距离计算评论者a发表的评论文本${{r}_{i}}$和${{r}_{j}}$间的相似度, 取最大值
异常评分
行为		 虚假评论者通过给出与正常评论者不一致的、甚至极端的评分, 达到提高或拉低评论对象综合评分的目的[9]。 极端评分[16]
(Extreme Rating, EXT)		 ${{f}_{EXT}}=\left\{ \begin{align} & 1,\text{*}({{r}_{a}},p({{r}_{a}}))\in \{1,5\} \\ & 0,\text{*}({{r}_{a}},p({{r}_{a}}))\in \{2,3,4\} \\ \end{align} \right.$ 判断评论者a是否总是对特定产品p给出极端评分。5星评价体中, 1星或5星为极端评分
积极评论比例[8]
(Percentage of Positive Reviews, PPR)		 ${{f}_{PPR}}=\frac{\left| \left\{ r\in {{R}_{a}}:\text{*}r\in \{4,5\} \right\} \right|}{\left| {{R}_{a}} \right|}$ 计算评论者a倾向于发布积极情感评论的程度。5星评价中, 评分≥4星的评论为积极评论
评分偏差[17]
(Rating Deviation, RD)		 ${{f}_{RD}}=\frac{\left| {{r}_{p,a}}-{{{\bar{r}}}_{p}} \right|}{4}$ 计算评论者a对某产品p的评分
rp,a与该产品平均评分${{\bar{r}}_{p}}$的不一
致程度。分母表示5星评价体系中的最大评分偏差为4
早期评论
行为		 虚假评论者倾向于在产品刚上线时对其进行评论[14], 可以最大程度地影响后来消费者对产品的印象。 早期评论[16]
(Early Time Frame,
ETF)		 ${{f}_{ETF}}=\left\{ \begin{align} & 0,L(a,p)-A(p)>\delta \\ & 1-\frac{L(a,p)-A(p)}{\delta }, 其他 \end{align} \right.$
 计算评论者a评论某产品p的早期程度。$L(a,p)$为最近评论时间, $A(p)$为产品上线时间, $\delta$为早期评论阈值, 估计值为7个月
头条评论比例[16]
(Ratio of First Review, RFR)		 ${{f}_{RFR}}=\frac{\left| \left\{ r\in {{R}_{a}}:r 是头条评论\right\} \right|}{\left| {{R}_{a}} \right|}$ 计算评论者a的所有评论中是头条评论的比例
突发评论
行为		 虚假评论者在较短时间间隔内多次发表评论, 以达到快速影响评论对象综合评分、操纵评论情感倾向的目的[16, 18]。 突发性发布[16]
(Reviewing Burstiness, RB)		 ${{f}_{RB}}=\left\{ \begin{align} & 0,L(a)-F(a)>\tau \\ & 1-\frac{L(a)-F(a)}{\tau }, 其他 \end{align} \right.$
 计算评论者a首次评论时间$L(a)$和最近一次评论时间$F(a)$的接近程度, τ为突发期阈值, 估计值为20天
突发评论比例[17]
(Burst Review Ratio, BRR)		 ${{f}_{BRR}}=\frac{\left| {{B}_{\text{a}}} \right|}{\left| {{R}_{\text{a}}} \right|}$ 计算评论者a所有评论中是突发评论的比例。Ba为评论者a所有评论中处于评论突发期的评论集合
单例评论者比例[19]
(Singleton Ratio, SR)		 ${{f}_{SR}}=\frac{\left| \left\{ r\in {{R}_{p}}:r 是单例评论\right\} \right|}{\left| {{R}_{p}} \right|}$
 单例评论者指只发表了一条评论的评论者, 其为虚假评论者的可能性高[18]。Rp为产品p的评论集合
频繁评论
行为		 正常评论者发布评论的时间和数量一般是随机的, 而虚假评论者由于执行特定的任务, 其评论时间和数量都有一定规律, 例如每天、每月都发表一定数量的评论[16]。 最大日发布评论数[16]
(Maximum Number of Reviews, MNR)		 ${{f}_{MNR}}=\frac{MaxRev(a)}{{{\max }_{a\in A}}(MaxRev(a))}$ 计算评论者a单日内发表最大评论数MaxRev(a)与其他评论者单日内发表最大评论数的比值
评论发布频繁度[20]
(Posting Frequency, PF)		 ${{f}_{PF}}=\mathrm{Max}\{a({{u}_{i}})\left| a({{u}_{i}})=a{{c}_{j}}({{u}_{i}})-avg({{u}_{i}}) \right.\}$ 计算评论者每月实际评论数acj(ui)与平均评论数avg(ui)的最大差值
针对性评
论行为		 正常评论者的评论对象通常是随机的, 而虚假评论者发表的评论则具有较强的针对性, 例如只对特定的产品、品牌或店铺进行评论[21]。 品牌偏离分[10]
(Brand Deviation Score, BDS)		 ${{f}_{BDS}}=\text{H(X)}=\underset{i}{\overset{n}{\mathop \sum }}\,p({{x}_{i}})\mathrm{log}p({{x}_{i}})$ 计算评论者在不同品牌上评论数的分布差异。xi代表第i个品牌, p(xi)为第i个品牌被评论的概率, 采用熵值衡量
离群产品评论比例[22]
(Ratio of Outlier Products Reviewing, ROPR)		 ${{f}_{ROPR}}=\frac{\left| \left\{ r\in {{R}_{a}}:r 是离群产品评论\right\} \right|}{\left| {{R}_{a}} \right|}$ 离群产品指只被一个评论者评论的产品。该特征计算评论者a所有评论中是离群产品评论的比例
评论密度[21]包括产品类别密度(Category Density, CD)、店铺密度(Store Density, SD)和时间密度(Time Density, TD) ${{f}_{CD}}=\frac{numReview{{(c)}_{r}}}{\left| {{R}_{a}} \right|}$
${{f}_{SD}}=\frac{numReview{{(s)}_{r}}}{\left| {{R}_{a}} \right|}$
${{f}_{TD}}=\frac{numDays(a)}{\left| {{R}_{a}} \right|}$		 计算评论者在特定产品类别、店铺或时间段上进行评论的密集程度
标注数据 方法 特征维度 代表性文献 识别效果 方法复杂度 说明
评论 评论者 关系
使用 LR √ [87, 93-94] 中 低 特征组合形式直观, 容易出现欠拟合
√ √ [9, 19, 56, 61]
SVM √ [7, 37, 39, 41-42, 50] 高 低 适用于处理高维特征空间问题, 分类性能高
√ √ [8, 49-52, 57]
RF √ [91] 高 中 适用于处理不平衡数据集问题, 减少过拟合
√ [26]
√ √ [89]
√ √ √ [25]
NB √ [63, 95-96] 高 低 模型简单、参数较少; 对数据稀疏性不敏感; 假设特征间是相互独立的, 但在实际问题中往往不成立
DT √ √ [21, 53] 高 低 模型计算简单, 可解释性强; 容易发生过拟合
MEM √ [38, 97] 高 低 约束条件设置灵活; 计算代价较大, 数据稀疏问题较严重
SAGE √ [12] 中 高 处理数据领域迁移能力较强
集成学习 √ [64, 88, 90] 高 高 提高分类稳定性和鲁棒性, 应对不平衡数据集问题
神经网络 √ [45-48] 高 高 自动学习文本特征, 无需人工设计特征; 需要大量参数, 学习时间较长
√ √ [28, 54, 56]
不使用 语义分析 √ [74-82] 低 中 虚假性判据简单, 误判率较高
聚类法 √ [67, 83-84] 高 中 聚类中簇的数目较难确定
MRF √ √ [33] 中 中 对网络结构有较强的拟合能力
√ √ √ [36]
时序分析 √ √ [18, 85] 高 中 可提高方法准确率和时间性能
部分使用 Co-training √ [69-70] 中 高 半监督方法, 适用于小数据集, 要求两个视图的特征具有独立性
√ √ [10, 32]
PU学习 √ [11, 71] 高 高 半监督方法, 适用于数据集包含少量正例及大量无标注数据的情况
√ √ √ [6]
[1] Cone Communication LLC. 2011 Online Influence Trend Tracker[R/OL]. [ 2011- 08- 30]. .
[2] Jindal N, Liu B . Review Spam Detection [C]// Proceedings of the 16th International Conference on World Wide Web, Alberta, Canada. ACM, 2007: 1189-1190.
[3] Ott M, Cardie C, Hancock J . Estimating the Prevalence of Deception in Online Review Communities [C]// Proceedings of the 21st International Conference on World Wide Web, Lyon, France. ACM, 2012: 201-210.
[4] Rastogi A, Mehrotra M . Opinion Spam Detection in Online Reviews[J]. Journal of Information & Knowledge Management, 2017,16(4):1750036.
[5] Kitchenham B . Procedures for Performing Systematic Reviews[R]. Keele University , 2004.
[6] Li H, Chen Z, Liu B , et al. Spotting Fake Reviews via Collective Positive-Unlabeled Learning [C]// Proceedings of the 14th IEEE International Conference on Data Mining. IEEE, 2014: 899-904.
[7] Ott M, Choi Y, Cardie C , et al. Finding Deceptive Opinion Spam by Any Stretch of the Imagination [C]// Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Portland, Oregon, USA. ACL, 2011: 309-319.
[8] Mukherjee A, Venkataraman V, Liu B , et al. What Yelp Fake Review Filter Might Be Doing? [C]// Proceedings of the 7th International AAAI Conference on Weblogs and Social Media. AAAI, 2013.
[9] Jindal N, Liu B . Opinion Spam and Analysis [C]// Proceedings of the 2008 International Conference on Web Search and Data Mining, Palo Alto, California, USA. ACM, 2008: 219-230.
[10] Li F, Huang M, Yang Y , et al. Learning to Identify Review Spam [C]// Proceedings of the 22nd International Joint Conference on Artificial Intelligence, Barcelona, Spain. AAAI, 2011: 2488-2493.
[11] Li H, Liu B, Mukherjee A , et al. Spotting Fake Reviews Using Positive-Unlabeled Learning[J]. Computación y Sistemas, 2014,18(3):467-475.
[12] Li J, Ott M, Cardie C , et al. Towards a General Rule for Identifying Deceptive Opinion Spam [C]// Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, Baltimore, Maryland, USA. ACL, 2014: 1566-1576.
[13] Ott M, Cardie C, Hancock J T . Negative Deceptive Opinion Spam [C]// Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Atlanta, Georgia, USA. ACL, 2013: 497-501.
[14] Lim E P, Nguyen V A, Jindal N , et al. Detecting Product Review Spammers Using Rating Behaviors [C]// Proceedings of the 19th ACM International Conference on Information and Knowledge Management, Toronto, Canada. ACM, 2010: 939-948.
[15] Mukherjee A, Liu B, Glance N . Spotting Fake Reviewer Groups in Consumer Reviews [C]// Proceedings of the 21st International Conference on World Wide Web, Lyon, France. ACM, 2012: 191-200.
[16] Mukherjee A, Kumar A, Liu B , et al. Spotting Opinion Spammers Using Behavioral Footprints [C]// Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Chicago, Illinois, USA. ACM, 2013: 632-640.
[17] Fei G, Mukherjee A, Liu B , et al. Exploiting Burstiness in Reviews for Review Spammer Detection [C]// Proceedings of the 7th International AAAI Conference on Weblogs and Social Media. AAAI, 2013.
[18] Xie S, Wang G, Lin S , et al. Review Spam Detection via Temporal Pattern Discovery [C]// Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Beijing, China. ACM, 2012: 823-831.
[19] 李晶, 吴国仕, 谢菲 , 等. 生活消费平台虚假评论识别模型的研究[J]. 电子学报, 2016,44(12):2855-2860.
[19] ( Li Jing, Wu Guoshi, Xie Fei , et al. Research of Fraud Review Detection Model on O2O Platform[J]. Acta Electronic Sinica, 2016,44(12):2855-2860.)
[20] 任亚峰, 姬东鸿, 尹兰 . 基于半监督学习算法的虚假评论识别研究[J]. 四川大学学报:工程科学版, 2014,46(3):62-69.
[20] ( Ren Yafeng, Ji Donghong, Yin Lan . Deceptive Reviews Detection Based on Semi-Supervised Learning Algorithm[J]. Journal of Sichuan University: Engineering Science Edition, 2014,46(3):62-69.)
[21] Li Y, Feng X, Zhang S . Detecting Fake Reviews Utilizing Semantic and Emotion Model [C]// Proceedings of the 3rd International Conference on Information Science and Control Engineering. IEEE, 2016: 317-320.
[22] Liang D, Liu X, Shen H . Detecting Spam Reviewers by Combing Reviewer Feature and Relationship [C]// Proceedings of the 2014 International Conference on Informative and Cybernetics for Computational Social Systems. IEEE, 2014: 102-107.
[23] 宋海霞, 严馨, 余正涛 , 等. 基于半监督主动学习的虚假评论检测[J]. 昆明理工大学学报:自然科学版, 2015,40(5):59-65.
[23] ( Song Haixia, Yan Xin, Yu Zhengtao , et al. Detection of Fake Reviews Based on Semi-Supervised Active Learning[J]. Journal of Kunming University of Science and Technology: Natural Science Edition, 2015,40(5):59-65.)
[24] Li H, Chen Z, Mukherjee A , et al. Analyzing and Detecting Opinion Spam on a Large-scale Dataset via Temporal and Spatial Patterns [C]// Proceedings of the 9th International AAAI Conference on Web and Social Media. AAAI, 2015.
[25] Zhang D, Zhou L, Kehoe J L , et al. What Online Reviewer Behaviors Really Matter? Effects of Verbal and Nonverbal Behaviors on Detection of Fake Online Reviews[J]. Journal of Management Information Systems, 2016,33(2):456-482.
[26] Rahman M, Carbunar B, Ballesteros J , et al. To Catch a Fake: Curbing Deceptive Yelp Ratings and Venues[J]. Statistical Analysis and Data Mining, 2015,8(3):147-161.
[27] Viviani M, Pasi G . Quantifier Guided Aggregation for the Veracity Assessment of Online Reviews[J]. International Journal of Intelligent Systems, 2017,32(5):481-501.
[28] Goswami K, Park Y, Song C . Impact of Reviewer Social Interaction on Online Consumer Review Fraud Detection[J]. Journal of Big Data, 2017, 4(1): Article No. 15.
[29] Zhang J, Kang D K . Detecting Spamming Stores by Analyzing Their Suspicious Behaviors [C]// Proceedings of the 17th International Conference on Advanced Communications Technology. IEEE, 2015: 502-507.
[30] Xue H, Li F, Seo H , et al. Trust-Aware Review Spam Detection [C]// Proceedings of the 14th IEEE International Conference on Trust, Security and Privacy in Computing and Communications. IEEE, 2015: 726-733.
[31] Wang G, Xie S, Liu B , et al. Review Graph Based Online Store Review Spammer Detection [C]// Proceedings of the 11th International Conference on Data Mining. IEEE, 2011: 1242-1247.
[32] Ye J, Akoglu L . Discovering Opinion Spammer Groups by Network Footprints [C]// Proceedings of the 2015 ACM Conference on Online Social Networks. 2015.
[33] Akoglu L, Chandy R, Faloutsos C . Opinion Fraud Detection in Online Reviews by Network Effects [C]// Proceedings of the 7th International AAAI Conference on Weblogs and Social Media. AAAI, 2013.
[34] Lu Y, Zhang J, Xiao Y , et al. Simultaneously Detecting Fake Reviews and Review Spammers Using Factor Graph Model [C]// Proceedings of the 5th Annual ACM Web Science Conference, Paris, France. ACM, 2013: 225-233.
[35] Shehnepoor S, Salehi M, Farahbakhsh R , et al. NetSpam: A Network-Based Spam Detection Framework for Reviews in Online Social Media[J]. IEEE Transactions on Information Forensics and Security, 2017,12(7):1585-1595.
[36] Rayana S, Akoglu L . Collective Opinion Spam Detection: Bridging Review Networks and Metadata [C]// Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Sydney, Australia. ACM, 2015: 985-994.
[37] Feng S, Banerjee R, Choi Y . Syntactic Stylometry for Deception Detection [C]// Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics, Jeju Island, Korea. ACL, 2012: 171-175.
[38] Xu Q, Zhao H . Using Deep Linguistic Features for Finding Deceptive Opinion Spam [C]// Proceedings of the 24th International Conference on Computational Linguistics. ACL, 2012: 1341-1350.
[39] Shojaee S, Muard M A A, Azman A B , et al. Detecting Deceptive Reviews Using Lexical and Syntactic Features [C]// Proceedings of the 13th International Conference on Intelligent Systems Design and Applications. IEEE, 2013: 53-58.
[40] Harris C G . Detecting Deceptive Opinion Spam Using Human Computation [C]// Proceedings of the Workshops at the 26th AAAI Conference on Artificial Intelligence. AAAI, 2012: 87-93.
[41] 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, Allahabad, India. ACM, 2015: 115-119.
[42] Karami A, Zhou B . Online Review Spam Detection by New Linguistic Features [C]// Proceedings of the 2015 iConference. 2015.
[43] Zhang W, Jiang Y, Yoshida T . Deep Context Identification of Deceptive Reviews Using Word Vectors [C]// Proceedings of the 17th International Symposium on Knowledge and Systems Sciences. 2016: 213-224.
[44] Hernández-Castaneda A, Calvo H . Deceptive Text Detection Using Continuous Semantic Space Models[J]. Intelligent Data Analysis, 2017,21(3):679-695.
[45] Ren Y, Zhang Y . Deceptive Opinion Spam Detection Using Neural Network [C]// Proceedings of the 26th International Conference on Computational Linguistics, Osaka, Japan. ACL, 2016: 140-150.
[46] Ren Y, Ji D . Neural Networks for Deceptive Opinion Spam Detection: An Empirical Study[J]. Information Sciences, 2017,385:213-224.
[47] Li L, Qin B, Ren W , et al. Document Representation and Feature Combination for Deceptive Spam Review Detection[J]. Neurocomputing, 2017,254:33-41.
[48] Sun C, Du Q, Tian G . Exploiting Product Related Review Features for Fake Review Detection[J]. Mathematical Problems in Engineering, 2016: Article ID 4935792.
[49] 李霄, 丁晟春 . 垃圾商品评论信息的识别研究[J]. 现代图书情报技术, 2013(1):63-68.
[49] ( Li Xiao, Ding Shengchun . Research on Review Spam Recognition[J]. New Technology of Library and Information Service, 2013(1):63-68.)
[50] 邓莎莎, 张朋柱, 张晓燕 , 等. 基于欺骗语言线索的虚假评论识别[J]. 系统管理学报, 2014,23(2):263-270.
[50] ( Deng Shasha, Zhang Pengzhu, Zhang Xiaoyan , et al. Deception Detection Based on Fake Linguistic Cues[J]. Journal of System & Management, 2014,23(2):263-270.)
[51] 游贵荣, 吴为, 钱沄涛 . 电子商务中垃圾评论检测的特征提取方法[J]. 现代图书情报技术, 2014(10):93-100.
[51] ( You Guirong, Wu Wei, Qian Yuntao . Feature Extraction Method for Detecting Spam in Electronic Commerce[J]. New Technology of Library and Information Service, 2014(10):93-100.)
[52] KC S, Mukherjee A . On the Temporal Dynamics of Opinion Spamming: Case Studies on Yelp [C]// Proceedings of the 25th International Conference on World Wide Web. ACM, 2016: 369-379.
[53] 赵静娴 . 网络交易垃圾评论智能识别研究[J]. 现代情报, 2016,36(4):57-61.
[53] ( Zhao Jingxian . Research on Intelligent Recognition of Network Transaction Review Spam[J]. Journal of Modern Information, 2016,36(4):57-61.)
[54] 皮琪, 王文杰, 杨飞 , 等. 基于深度学习的虚假评论识别[J]. 网络新媒体技术, 2016,5(6):30-33.
[54] ( Pi Qi, Wang Wenjie, Yang Fei , et al. Spam Review Detection Based on Deep Learning Framework[J]. Journal of Network New Media, 2016,5(6):30-33.)
[55] Wang X, Liu K, He S , et al. Learning to Represent Review with Tensor Decomposition for Spam Detection [C]// Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. ACL, 2016: 866-875.
[56] Wang X, Liu K, Zhao J . Handing Cold-Start Problem in Review Spam Detection by Jointly Embedding Texts and Behaviors [C]// Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. ACL, 2017: 366-376.
[57] Lin Y, Zhu T, Wu H , et al. Towards Online Anti-Opinion Spam: Spotting Fake Reviews from the Review Sequence [C]// Proceedings of the 2014 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining. ACM, 2014.
[58] 陈燕方 . 基于DDAG-SVM的在线商品评论可信度分类模型[J]. 情报理论与实践, 2017,40(7):132-137.
[58] ( Chen Yanfang . Research on Reliability Classification Model of Online Product Reviews Based on DDAG-SVM[J]. Information Studies: Theory & Application, 2017,40(7):132-137.)
[59] Heredia B, Khoshgoftaar T M, Prusa J D , et al. Improving Detection of Untrustworthy Online Reviews Using Ensemble Learners Combined with Feature Selection[J]. Social Network Analysis and Mining, 2017,7:37.
[60] Wu G, Greene D, Cunningham P . Merging Multiple Criteria to Identify Suspicious Reviews [C]// Proceedings of the 4th ACM Conference on Recommender Systems, Barcelona, Spain. ACM, 2010: 241-244.
[61] 吴敏, 何珑 . 融合多特征的产品垃圾评论识别[J]. 微型机与应用, 2012,31(22):85-87, 90.
[61] ( Wu Min, He Long . Fuse Multi-features to Identify Product Review Spam[J]. Microcomputers & Its Applications, 2012,31(22):85-87, 90.)
[62] Koven J, Siadati H, Lin C Y Finding Valuable Yelp Comments by Personality, Content, Geo, and Anomaly Analysis [C]// Proceedings of the 2014 IEEE International Conference on Data Mining Workshop. IEEE, 2014: 1215-1218.
[63] Patel R, Thakkar P . Opinion Spam Detection Using Feature Selection [C]// Proceedings of the 6th International Conference on Computational Intelligence and Communication Networks. IEEE, 2014: 560-564.
[64] Banerjee S, Chua A Y K, Kim J J . Distinguishing Between Authentic and Fictitious User-generated Hotel Reviews [C]// Proceedings of the 6th International Conference on Computing, Communications and Networking Technologies. IEEE, 2015: 1-7.
[65] Banerjee S Chua A Y K, Kim J J . Don’t Be Deceived: Using Linguistic Analysis to Learn How to Discern Online Review Authenticity[J]. Journal of the Association for Information Science and Technology, 2017,68(6):1525-1538.
[66] Crawford M, Khoshgoftaar T M, Prusa J D . Reducing Feature Set Explosion to Facilitate Real-World Review Spam Detection [C]// Proceedings of the 29th International Florida Artificial Intelligence Research Society Conference. AAAI, 2016.
[67] 任亚峰, 尹兰, 姬东鸿 . 基于语言结构和情感极性的虚假评论识别[J]. 计算机科学与探索, 2014,8(3):313-320.
[67] ( Ren Yafeng, Yin Lan, Ji Donghong . Deceptive Reviews Detection Based on Language Structure and Sentiment Polarity[J]. Journal of Frontiers of Computer Science and Technology, 2014,8(3):313-320.)
[68] Li J, Cardie C, Li S . TopicSpam: A Topic-Model Based Approach for Spam Detection [C]// Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics. ACL, 2013: 217-221.
[69] Zhang W, Bu C, Yoshida T , et al. CoFea: A Novel Approach to Spam Review Identification Based on Entropy and Co-Training[J]. Entropy, 2016,18(12):429.
[70] Zhang W, Bu C, Yoshida T , et al. CoSpa: A Co-training Approach for Spam Review Identification with Support Vector Machine[J]. Information, 2016,7(1):12.
[71] Hernández-Fusilier D, Montes-y-Gómez M, Rosso P . Using PU-Learning to Detect Deceptive Opinion Spam [C]// Proceedings of the 4th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis. ACL, 2013: 38-45.
[72] Hernández-Fusilier D, Montes-y-Gómez M, Rosso P , et al. Detecting Positive and Negative Deceptive Opinions Using PU-learning[J]. Information Processing and Management, 2015,51(4):433-443.
[73] 任亚峰, 姬东鸿, 张红斌 , 等. 基于PU学习算法的虚假评论识别研究[J]. 计算机研究与发展, 2015,52(3):639-648.
[73] ( Ren Yafeng, Ji Donghong, Zhang Hongbin , et al. Deceptive Reviews Detection Based on Positive and Unlabeled Learning[J]. Journal of Computer Research and Development, 2015,52(3):639-648.)
[74] Algur S P, Patil A P, Hiremath P S , et al. Conceptual Level Similarity Measure Based Review Spam Detection [C]// Proceedings of the 2010 International Conference on Signal and Image Processing. IEEE, 2010: 416-423.
[75] Lai C L, Xu K Q, Lau R Y K , et al. Toward a Language Modeling Approach for Consumer Review Spam Detection [C]// Proceedings of the 7th International Conference on E-Business Engineering. IEEE, 2010.
[76] Lai C L, Xu K Q, Lau R Y K , et al. High-Order Concept Associations Mining and Inferential Language Modeling for Online Review Spam Detection [C]// Proceedings of the 2010 IEEE International Conference on Data Mining Workshops. IEEE, 2010: 1120-1127.
[77] Lau R Y K, Liao S Y, Kwok R C W , et al. Text Mining and Probabilistic Language Modeling for Online Review Spam Detection[J]. ACM Transaction on Management Information Systems, 2012, 2(4): Article No. 25.
[78] 彭庆喜, 钱铁云 . 基于量化情感的网店垃圾评论检测[J]. 山东大学学报: 理学版, 2013,48(11):66-72.
[78] ( Peng Qingxi, Qian Tieyun . Store Review Spam Detection Based on Quantitative Sentiment[J]. Journal of Shandong University: Natural Science, 2013,48(11):66-72.)
[79] 陈燕方, 李志宇 . 基于评论产品属性情感倾向评估的虚假评论识别研究[J]. 现代图书情报技术, 2014(9):81-90.
[79] ( Chen Yanfang, Li Zhiyu . Research on Product Review Attribute-Based of Emotion Evaluate Review Spam Detection[J]. New Technology of Library and Information Service, 2014(9):81-90.)
[80] Sharma K, Lin K I . Review Spam Detector with Rating Consistency Check[C]// Proceedings of the 51st ACM Southeast Conference, Savannah, Georgia, USA. ACM, 2013: Article No. 34.
[81] Zhiyuli A, Liang X, Wang Y . Discerning the Trend: Concealing Deceptive Reviews [C]// Proceedings of the 2015 IEEE International Conference on Systems, Man, and Cybernetics. IEEE, 2015: 1833-1838.
[82] Algur S P, Biradar J G . Rating Consistency and Review Content Based Multiple Stores Review Spam Detection [C]// Proceedings of the 2015 International Conference on Information Processing. IEEE, 2015: 685-690.
[83] 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, 2013,49(4):433-438.
[83] ( Song Haixia, Yan Xin, Yu Zhengtao , et al. Detection of Fake Reviews Based on Adaptive Clustering[J]. Journal of Nanjing University: Natural Science, 2013,49(4):433-438.)
[84] 邓松, 万常选, 关爱浩 , 等. 基于行为与内容的科技产品虚假评论识别[J]. 小型微型计算机系统, 2015,36(11):2498-2503.
[84] ( Deng Song, Wan Changxuan, Guan Aihao , et al. Deceptive Reviews Detection of Technology Products Based on Behavior and Content[J]. Journal of Chinese Computer Systems, 2015,36(11):2498-2503.)
[85] Heydari A, Tavakoli M A, Salim N . Detection of Fake Opinions Using Time Series[J]. Expert Systems with Applications, 2016,58:83-92.
[86] Feng S, Xing L, Gogar A , et al. Distributional Footprints of Deceptive Product Reviews [C]// Proceedings of the 6th International AAAI Conference on Weblogs and Social Media. AAAI, 2012: 98-105.
[87] Banerjee S, Chua A Y K, Kim J J . Using Supervised Learning to Classify Authentic and Fake Online Reviews[C]// Proceedings of the 9th International Conference on Ubiquitous Information Management and Communication, Bali, Indonesia. ACM, 2015: Article No. 88.
[88] Heredia B, Khoshgoftaar T M, Prusa J D , et al. An Investigation of Ensemble Techniques for Detection of Spam Reviews [C]// Proceedings of the 15th International Conference on Machine Learning and Applications. IEEE, 2016: 127-133.
[89] 何珑 . 基于随机森林的产品垃圾评论识别[J]. 中文信息学报, 2015,29(3):150-154, 161.
[89] ( He Long . Identification of Product Review Spam by Random Forest[J]. Journal of Chinese Information Processing, 2015,29(3):150-154, 161.)
[90] Al Najada H, Zhu X . iSRD: Spam Review Detection with Imbalanced Data Distributions [C]// Proceedings of the 15th International Conference on Information Reuse and Integration. IEEE, 2014: 553-560.
[91] 昝红英, 毕银龙, 石金铭 . 基于Adaboost算法与规则匹配的垃圾评论识别[J]. 郑州大学学报:理学版, 2017,49(1):24-28.
[91] ( Zan Hongying, Bi Yinlong, Shi Jinming . Spam Review Identification Based on Adaboost Algorithm and Rules Matching[J]. Journal of Zhengzhou University: Natural Science Edition, 2017,49(1):24-28.)
[92] Ren Y, Ji D, Yin L , et al. Finding Deceptive Opinion Spam by Correcting the Mislabeled Instances[J]. Chinese Journal of Electronics, 2015,24(1):52-57.
[93] Li X, Yan X . A Novel Chinese Text Mining Method for E-Commerce Review Spam Detection [C]// Proceedings of the 17th International Conference on Web-Age Information Management. 2016: 95-106.
[94] Banerjee S, Chua A Y K . Applauses in Hotel Reviews: Genuine or Deceptive? [C]// Proceedings of the 2014 Science and Information Conference, London, UK. 2014: 938-942.
[95] Sun H, Morales A, Yan X . Synthetic Review Spamming and Defense [C]// Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Chicago, Illinois, USA. ACM, 2013: 1088-1096.
[96] Hernández-Fusilier D, Montes-y-Gómez M, Rosso P , et al. Detection of Opinion Spam with Character n-grams [C] //Proceedings of the 16th International Conference of Computational Linguistics and Intelligent Text Processing. 2015: 285-294.
[97] Chen C, Zhao H, Yang Y . Deceptive Opinion Spam Detection Using Deep Level Linguistic Features [C]// Proceedings of the 4th CCF Conference on Natural Language Processing and Chinese Computing. 2015: 465-474.
[98] Hernández-Castaneda A, Calvo H, Gelbukh A , et al. Cross-domain Deception Detection Using Support Vector Networks[J]. Soft Computing, 2017,21(3):585-595.
[99] Crawford M, Khoshgoftaar T M, Prusa J D , et al. Survey of Review Spam Detection Using Machine Learning Techniques[J]. Journal of Big Data, 2015, 2(1): Article No. 23.
[100] Kumar S, Hooi B, Makhija D , et al.FairJudge: Trustworthy User Prediction in Rating Platforms[OL]. arXiv Preprint, arXiv: 1703.10545.
[1] Nie Hui, Wang Jiajia. Review of Product Review Spams Detection[J]. 现代图书情报技术, 2014, 30(2): 63-71.
[2] You Guirong, Wu Wei, Qian Yuntao. Feature Extraction Method for Detecting Spam in Electronic Commerce[J]. 现代图书情报技术, 2014, 30(10): 93-100.
[3] Li Xiao, Ding Shengchun. Research on Review Spam Recognition[J]. 现代图书情报技术, 2013, 29(1): 63-68.
  Copyright © 2016 Data Analysis and Knowledge Discovery   Tel/Fax:(010)82626611-6626，82624938   E-mail:jishu@mail.las.ac.cn