产品垃圾评论识别研究综述
|
摘要
着重梳理当前产品垃圾评论识别的国内外研究,总结研究特点与不足,发掘发展趋势。在中国知网、Web of Science上以"虚假评论""review spam"等为关键词检索并筛选得到54篇国内外相关文献,采用文献分析法对其进行分类分析,重点阐述研究在识别特征和识别方法方面的优化创新,以及针对垃圾评论、垃圾评论发布者、发布群体等不同识别对象的方法差异。研究发现,当前垃圾评论识别的相关成果可以分为基于评论内容的方法和基于评论结构、评论者、被评论产品的方法,在未来的垃圾评论识别中,应根据数据集的特点,提取有效识别特征,选择优化识别方法。
The current research on identification of product spam comments at home and abroad is discussed and the characteristics of the research methods,deficiencies and the development trend are summarized. Fifty-four related literatures were retrieved and screened on CNKI and Web of Science by using the keywords of "fake review"and "review spam". Literature analysis is used to classify and analyze the literature. The optimization and innovation of research on identification features and identification methods,as well as the differences of identification methods for different objects such as spam comments,spam reviewers are emphasized. It is found that the methods current research used can be divided into content-based methods and methods based on the structure of comments,reviewers and commented products. In the future research,effective identification features with multi-dimensions should be picked up and methods should be optimized according to the characteristics of data sets.
The current research on identification of product spam comments at home and abroad is discussed and the characteristics of the research methods,deficiencies and the development trend are summarized. Fifty-four related literatures were retrieved and screened on CNKI and Web of Science by using the keywords of "fake review"and "review spam". Literature analysis is used to classify and analyze the literature. The optimization and innovation of research on identification features and identification methods,as well as the differences of identification methods for different objects such as spam comments,spam reviewers are emphasized. It is found that the methods current research used can be divided into content-based methods and methods based on the structure of comments,reviewers and commented products. In the future research,effective identification features with multi-dimensions should be picked up and methods should be optimized according to the characteristics of data sets.
引文
[1]JINDAL N,LIU B. Review spam detection[C]//International Conference on World Wide Web. New York:ACM,2007:1189-90.
[2]JINDAL N,LIU B. Analyzing and detecting review spam[C]//IEEE International Conference on Data Mining. Washington DC:IEEE,2007:547-552.
[3]孙升芸,田萱.产品垃圾评论检测研究综述[J].计算机科学,2011,38(Z10):198-201.
[4]聂卉,王佳佳.产品评论垃圾识别研究综述[J].数据分析与知识发现,2014,30(2):63-71.
[5]HEYDARI A,TAVAKOLI M A,SALIM N,et al. Detection of review spam:a survey[J]. Expert Systems with Applications,2015,42(7):3634-3642.
[6]DEWANG R K,SINGH A K. State-of-art approaches for review spammer detection:a survey[J]. Journal of Intelligent Information Systems,2018,50(2):231-264.
[7] RESHMA P R. Survey on spam detection techniques in online review systems[J]. Imperial Journal of Interdisciplinary Research,2017,3(2):1140-1143.
[8]SHARMA K,LIN K I. Review spam detector with rating consistency check[C]//ACM Southeast Conference. New York:ACM,2013:1-6.
[9]CAGNINA L C,ROSSO P. Detecting deceptive opinions:Intra and cross-domain classification using an efficient representation[J]. International Journal of Uncertainty,Fuzziness and Knowledge-Based Systems,2017,25(Suppl. 2):151-174.
[10] NARAYAN R,ROUT J K,JENA S K. Review spam detection using opinion mining[C]//SA P,SAHOO M,MURUGAPPAN M,et al. Progress in Intelligent Computing Techniques:Theory,Practice,and Applications. Singapore:Springer,2018:273-279.
[11]KARAMI A,ZHOU B. Online review spam detection by new linguistic features[C]//Iconference. California:i Schools,2015:1-5.
[12] LAU R Y K,LIAO S Y,KWOK C W,et al. Text mining and probabilistic language modeling for online review spam detection[J]. Acm Transactions on Management Information Systems,2012,2(4):1-30.
[13]谭文堂,朱洪,葛斌,等.垃圾评论自动过滤方法[J].国防科技大学学报,2012,34(5):153-157.
[14]MORALES A,SUN H,YAN X. Synthetic review spamming and defense[C]//International Conference on World Wide Web. New York:ACM,2013:155-156.
[15]LI X,YAN X W. A novel Chinese text mining method for e-commerce review spam detection[C]//CUI B,ZHANG N,XU J,et al. Web-Age Information Management. Nanchang:Springer,2016:95-106.
[16]LI L Y,REN W J,QIN B,et al. Learning document representation for deceptive opinion spam detection[C]//SUN M,LIU Z,ZHANG M,et al. Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data. Guangzhou:Springer,2015:393-404.
[17]DANDIBHOTLA T S. Finding and classifying the deceptive spam reviews using LIWC dictionary variables and decision tree classifier[J]. International Journal of Engineering&Technology,2018,10(1):308-315.
[18] BANERJEE S,CHUA A Y K. Applauses in hotel reviews:genuine or deceptive?[C]//Science and Information Conference. Washington DC:IEEE,2015:938-942.
[19]ZHANG W,JIANG Y P,YOSHIDA T. Deep context identification of deceptive reviews using word vectors[C]//CHEN J,NAKAMORI Y,YUE W,et al. Knowledge and Systems Sciences. Kobe:Springer,2016:213-224.
[20]SIAGIAN A H A M,ARITSUGI M. Combining word and character n-grams for detecting deceptive opinions[C]//Computer Software and Applications Conference. Washington DC:IEEE,2017:828-833.
[21]REN Y,JI D. Neural networks for deceptive opinion spam detection:an empirical study[J]. Information Sciences,2017,385-386:213-224.
[22]LI H,LIU B,MUKHERJEE A,et al. Spotting fake reviews using positive-unlabeled learning[J]. Computacion y Sistemas,2015,18(3):467-475.
[23]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.
[24] MAYZLIN D,DOVER Y,CHEVALIER J. Promotional reviews:an empirical investigation of online review manipulation[J]. American Economic Review,2014,104(8):2421-2455.
[25]OTT M,CHOI Y,CARDIE C,et al. Finding deceptive opinion spam by any stretch of the imagination[C]//Meeting of the Association for Computational Linguistics:Human Language Technologies. Stroudsburg:2011:309-319.
[26]NAJADA H A,ZHU X. i SRD:spam review detection with imbalanced data distributions[C]//IEEE International Conference on Information Reuse and Integration. Washington DC:IEEE,2014:553-60.
[27]DONG B,LIU Q,FU Y,et al. A research of Taobao cheater detection[C]//13th Conference on E-Business,E-Services and E-Society. Sanya:Springer,2014:338-345.
[28]YUAN Y,XIE S,LU C T,et al. Interpretable and effective opinion spam detection via temporal patterns mining across websites[C]//IEEE International Conference on Big Data. Washington DC:IEEE,2016:96-105.
[29]JINDAL N,LIU B. Opinion spam and analysis[C]//International Conference on Web Search&Data Mining. New York:ACM,2008:219-230.
[30]MUKHERJEE A,LIU B,WANG J,et al. Detecting group review spam[C]//International Conference Companion on World Wide Web. New York:ACM,2011:93-94.
[31]ANSARI G,AHMAD T,DOJA M N. Review ranking method for spam recognition[C]//GOEL S,SANGHI D,ZOMAYA A Y,et al. Ninth International Conference on Contemporary Computing. Washington:IEEE,2016:290-294.
[32]LI F,HUANG M,YANG Y,et al. Learning to identify review spam[C]//International Joint Conference on Artificial Intelligence. Catalonia:ACM,2011:2488-2493.
[33]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.
[34]XIE S,WANG G,LIN S,et al. Review spam detection via temporal pattern discovery[C]//ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York:ACM,2012:823-31.
[35]XU C,ZHANG J. Combating product review spam campaigns via multiple heterogeneous pairwise features[C]//Proceedings of the 2015 SIAM International Conference on Data Mining. Society for Industrial and Applied Mathematics. Vancouver:Society for Industrial and Applied Mathematics,2015:172-180.
[36]LI H,CHEN Z,MUKHERJEE A,et al. Analyzing and detecting opinion spam on a large-scale dataset via temporal and spatial patterns[C]//International AAAI Conference on Web and Social Media. Oxford,England:AAAI Press,2015:634-637.
[37]KUMAR N,VENUGOPA D,QIU L,et al. Detecting review manipulation on online platforms with hierarchical supervised learning[J]. Journal of Management Information Systems,2018,35(1):350-380.
[38]HEYDARI A,TAVAKOLI M,SALIM N. Detection of fake opinions using time series[J]. Expert Systems with Applications,2016,58:83-92.
[39]LIN Y,ZHU T,WANG X,et al. Towards online review spam detection[C]//International Conference on World Wide Web.New York:ACM,2014:341-342.
[40]SAVAGE D,ZHANG X Z,YU X H,et al. Detection of opinion spam based on anomalous rating deviation[J]. Expert Systems with Applications,2015,42(22):8650-8657.
[41]HOOI B,SHIN K,SONG H A,et al. Graph-based fraud detection in the face of camouflage[J]. Acm Transactions on Knowledge Discovery from Data,2017,11(4):1-26.
[42]AKOGLU L,CHANDY R,FALOUTSOS C. Opinion fraud detection in online reviews by network effects[C]//International AAAI Conference on Weblogs and Social Media. Massachusetts:AAAI Press,2103:2-11.
[43]ZHANG Q,WU J,ZHANG P,et al. Collective hyping detection system for identifying online spam activities[J]. IEEE Intelligent Systems,2017,32(5):53-63.
[44] WANG G,XIE S,LIU B,et al. Review graph based online store review spammer detection[C]//IEEE International Conference on Data Mining. Washington DC:IEEE,2011:1242-1247.
[45]王琢,李准,徐野,等.基于评论图的虚假产品评论人的检测[J].计算机科学,2014,41(10):295-299.
[46]RAYANA S,AKOGLU L. Collective opinion spam detection:bridging review networks and metadata[C]//ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York:ACM,2015:985-994.
[47]GUO B,WANG H,YU Z,et al. Detecting spammers in e-commerce website via spectrum features of user relation graph[C]//International Conference on Advanced Cloud and Big Data. Washington DC:IEEE,2017:324-30.
[48]WANG Z,GU S,ZHAO X,et al. Graph-based review spammer group detection[J]. Knowledge&Information Systems,2018,55(3):571-597.
[49]YE J,AKOGLU L. Discovering opinion spammer groups by network footprints[C]//APPICE A,RODRIGUES P,SANTOS COSTA V,et al. Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Porto:Springer Cham,2015:267-282.
[50]WU X,DONG Y X,TAO J,et al. Reliable fake review detection via modeling temporal and behavioral patterns[C]//IEEE International Conference on Big Data. Washington DC:IEEE,2017:494-499.
[51] EIMURRIGI E,GHERBI A. An empirical study on detecting fake reviews using machine learning techniques[C]//International Conference on Innovative Computing Technology. Washington DC:IEEE,2017:107-114.
[52]ZHANG L,WU Z,CAO J. Detecting spammer groups from product reviews:a partially supervised learning model[C]//IEEE Access. Washington DC:IEEE,2018:2559-2568.
[53]DO Q N T,HUSSAIN F K,BANG T N. A fuzzy approach to detect spammer groups[C]//IEEE International Conference on Fuzzy Systems. Washington DC:IEEE,2107:1-6.
[2]JINDAL N,LIU B. Analyzing and detecting review spam[C]//IEEE International Conference on Data Mining. Washington DC:IEEE,2007:547-552.
[3]孙升芸,田萱.产品垃圾评论检测研究综述[J].计算机科学,2011,38(Z10):198-201.
[4]聂卉,王佳佳.产品评论垃圾识别研究综述[J].数据分析与知识发现,2014,30(2):63-71.
[5]HEYDARI A,TAVAKOLI M A,SALIM N,et al. Detection of review spam:a survey[J]. Expert Systems with Applications,2015,42(7):3634-3642.
[6]DEWANG R K,SINGH A K. State-of-art approaches for review spammer detection:a survey[J]. Journal of Intelligent Information Systems,2018,50(2):231-264.
[7] RESHMA P R. Survey on spam detection techniques in online review systems[J]. Imperial Journal of Interdisciplinary Research,2017,3(2):1140-1143.
[8]SHARMA K,LIN K I. Review spam detector with rating consistency check[C]//ACM Southeast Conference. New York:ACM,2013:1-6.
[9]CAGNINA L C,ROSSO P. Detecting deceptive opinions:Intra and cross-domain classification using an efficient representation[J]. International Journal of Uncertainty,Fuzziness and Knowledge-Based Systems,2017,25(Suppl. 2):151-174.
[10] NARAYAN R,ROUT J K,JENA S K. Review spam detection using opinion mining[C]//SA P,SAHOO M,MURUGAPPAN M,et al. Progress in Intelligent Computing Techniques:Theory,Practice,and Applications. Singapore:Springer,2018:273-279.
[11]KARAMI A,ZHOU B. Online review spam detection by new linguistic features[C]//Iconference. California:i Schools,2015:1-5.
[12] LAU R Y K,LIAO S Y,KWOK C W,et al. Text mining and probabilistic language modeling for online review spam detection[J]. Acm Transactions on Management Information Systems,2012,2(4):1-30.
[13]谭文堂,朱洪,葛斌,等.垃圾评论自动过滤方法[J].国防科技大学学报,2012,34(5):153-157.
[14]MORALES A,SUN H,YAN X. Synthetic review spamming and defense[C]//International Conference on World Wide Web. New York:ACM,2013:155-156.
[15]LI X,YAN X W. A novel Chinese text mining method for e-commerce review spam detection[C]//CUI B,ZHANG N,XU J,et al. Web-Age Information Management. Nanchang:Springer,2016:95-106.
[16]LI L Y,REN W J,QIN B,et al. Learning document representation for deceptive opinion spam detection[C]//SUN M,LIU Z,ZHANG M,et al. Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data. Guangzhou:Springer,2015:393-404.
[17]DANDIBHOTLA T S. Finding and classifying the deceptive spam reviews using LIWC dictionary variables and decision tree classifier[J]. International Journal of Engineering&Technology,2018,10(1):308-315.
[18] BANERJEE S,CHUA A Y K. Applauses in hotel reviews:genuine or deceptive?[C]//Science and Information Conference. Washington DC:IEEE,2015:938-942.
[19]ZHANG W,JIANG Y P,YOSHIDA T. Deep context identification of deceptive reviews using word vectors[C]//CHEN J,NAKAMORI Y,YUE W,et al. Knowledge and Systems Sciences. Kobe:Springer,2016:213-224.
[20]SIAGIAN A H A M,ARITSUGI M. Combining word and character n-grams for detecting deceptive opinions[C]//Computer Software and Applications Conference. Washington DC:IEEE,2017:828-833.
[21]REN Y,JI D. Neural networks for deceptive opinion spam detection:an empirical study[J]. Information Sciences,2017,385-386:213-224.
[22]LI H,LIU B,MUKHERJEE A,et al. Spotting fake reviews using positive-unlabeled learning[J]. Computacion y Sistemas,2015,18(3):467-475.
[23]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.
[24] MAYZLIN D,DOVER Y,CHEVALIER J. Promotional reviews:an empirical investigation of online review manipulation[J]. American Economic Review,2014,104(8):2421-2455.
[25]OTT M,CHOI Y,CARDIE C,et al. Finding deceptive opinion spam by any stretch of the imagination[C]//Meeting of the Association for Computational Linguistics:Human Language Technologies. Stroudsburg:2011:309-319.
[26]NAJADA H A,ZHU X. i SRD:spam review detection with imbalanced data distributions[C]//IEEE International Conference on Information Reuse and Integration. Washington DC:IEEE,2014:553-60.
[27]DONG B,LIU Q,FU Y,et al. A research of Taobao cheater detection[C]//13th Conference on E-Business,E-Services and E-Society. Sanya:Springer,2014:338-345.
[28]YUAN Y,XIE S,LU C T,et al. Interpretable and effective opinion spam detection via temporal patterns mining across websites[C]//IEEE International Conference on Big Data. Washington DC:IEEE,2016:96-105.
[29]JINDAL N,LIU B. Opinion spam and analysis[C]//International Conference on Web Search&Data Mining. New York:ACM,2008:219-230.
[30]MUKHERJEE A,LIU B,WANG J,et al. Detecting group review spam[C]//International Conference Companion on World Wide Web. New York:ACM,2011:93-94.
[31]ANSARI G,AHMAD T,DOJA M N. Review ranking method for spam recognition[C]//GOEL S,SANGHI D,ZOMAYA A Y,et al. Ninth International Conference on Contemporary Computing. Washington:IEEE,2016:290-294.
[32]LI F,HUANG M,YANG Y,et al. Learning to identify review spam[C]//International Joint Conference on Artificial Intelligence. Catalonia:ACM,2011:2488-2493.
[33]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.
[34]XIE S,WANG G,LIN S,et al. Review spam detection via temporal pattern discovery[C]//ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York:ACM,2012:823-31.
[35]XU C,ZHANG J. Combating product review spam campaigns via multiple heterogeneous pairwise features[C]//Proceedings of the 2015 SIAM International Conference on Data Mining. Society for Industrial and Applied Mathematics. Vancouver:Society for Industrial and Applied Mathematics,2015:172-180.
[36]LI H,CHEN Z,MUKHERJEE A,et al. Analyzing and detecting opinion spam on a large-scale dataset via temporal and spatial patterns[C]//International AAAI Conference on Web and Social Media. Oxford,England:AAAI Press,2015:634-637.
[37]KUMAR N,VENUGOPA D,QIU L,et al. Detecting review manipulation on online platforms with hierarchical supervised learning[J]. Journal of Management Information Systems,2018,35(1):350-380.
[38]HEYDARI A,TAVAKOLI M,SALIM N. Detection of fake opinions using time series[J]. Expert Systems with Applications,2016,58:83-92.
[39]LIN Y,ZHU T,WANG X,et al. Towards online review spam detection[C]//International Conference on World Wide Web.New York:ACM,2014:341-342.
[40]SAVAGE D,ZHANG X Z,YU X H,et al. Detection of opinion spam based on anomalous rating deviation[J]. Expert Systems with Applications,2015,42(22):8650-8657.
[41]HOOI B,SHIN K,SONG H A,et al. Graph-based fraud detection in the face of camouflage[J]. Acm Transactions on Knowledge Discovery from Data,2017,11(4):1-26.
[42]AKOGLU L,CHANDY R,FALOUTSOS C. Opinion fraud detection in online reviews by network effects[C]//International AAAI Conference on Weblogs and Social Media. Massachusetts:AAAI Press,2103:2-11.
[43]ZHANG Q,WU J,ZHANG P,et al. Collective hyping detection system for identifying online spam activities[J]. IEEE Intelligent Systems,2017,32(5):53-63.
[44] WANG G,XIE S,LIU B,et al. Review graph based online store review spammer detection[C]//IEEE International Conference on Data Mining. Washington DC:IEEE,2011:1242-1247.
[45]王琢,李准,徐野,等.基于评论图的虚假产品评论人的检测[J].计算机科学,2014,41(10):295-299.
[46]RAYANA S,AKOGLU L. Collective opinion spam detection:bridging review networks and metadata[C]//ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York:ACM,2015:985-994.
[47]GUO B,WANG H,YU Z,et al. Detecting spammers in e-commerce website via spectrum features of user relation graph[C]//International Conference on Advanced Cloud and Big Data. Washington DC:IEEE,2017:324-30.
[48]WANG Z,GU S,ZHAO X,et al. Graph-based review spammer group detection[J]. Knowledge&Information Systems,2018,55(3):571-597.
[49]YE J,AKOGLU L. Discovering opinion spammer groups by network footprints[C]//APPICE A,RODRIGUES P,SANTOS COSTA V,et al. Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Porto:Springer Cham,2015:267-282.
[50]WU X,DONG Y X,TAO J,et al. Reliable fake review detection via modeling temporal and behavioral patterns[C]//IEEE International Conference on Big Data. Washington DC:IEEE,2017:494-499.
[51] EIMURRIGI E,GHERBI A. An empirical study on detecting fake reviews using machine learning techniques[C]//International Conference on Innovative Computing Technology. Washington DC:IEEE,2017:107-114.
[52]ZHANG L,WU Z,CAO J. Detecting spammer groups from product reviews:a partially supervised learning model[C]//IEEE Access. Washington DC:IEEE,2018:2559-2568.
[53]DO Q N T,HUSSAIN F K,BANG T N. A fuzzy approach to detect spammer groups[C]//IEEE International Conference on Fuzzy Systems. Washington DC:IEEE,2107:1-6.