{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T19:37:12Z","timestamp":1780774632783,"version":"3.54.1"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2015,10,5]],"date-time":"2015-10-05T00:00:00Z","timestamp":1444003200000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Journal of Big Data"],"published-print":{"date-parts":[[2015,12]]},"DOI":"10.1186\/s40537-015-0029-9","type":"journal-article","created":{"date-parts":[[2015,10,5]],"date-time":"2015-10-05T05:30:48Z","timestamp":1444023048000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":382,"title":["Survey of review spam detection using machine learning techniques"],"prefix":"10.1186","volume":"2","author":[{"given":"Michael","family":"Crawford","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taghi M.","family":"Khoshgoftaar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joseph D.","family":"Prusa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aaron N.","family":"Richter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hamzah","family":"Al Najada","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2015,10,5]]},"reference":[{"issue":"4","key":"29_CR1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2070710.2070716","volume":"2","author":"RY Lau","year":"2011","unstructured":"Lau RY, Liao SY, Kwok RCW, Xu K, Xia Y, Li Y (2011) Text mining and probabilistic language modeling for online review spam detecting. ACM Trans Manage Inf Syst 2(4):1\u201330","journal-title":"ACM Trans Manage Inf Syst"},{"key":"29_CR2","first-page":"0975","volume":"4","author":"S Dixit","year":"2013","unstructured":"Dixit S, Agrawal AJ (2013) Survey on review spam detection. Int J Comput Commun Technol ISSN (PRINT) 4:0975\u20137449","journal-title":"Int J Comput Commun Technol ISSN (PRINT)"},{"key":"29_CR3","unstructured":"Ott M, Choi Y, Cardie C, Hancock JT (2011) Finding deceptive opinion spam by any stretch of the imagination. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies-Volume 1 (pp. 309\u2013319). Association for Computational Linguistics"},{"key":"29_CR4","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1016\/j.fss.2014.01.015","volume":"258","author":"V L\u00f3pez","year":"2015","unstructured":"L\u00f3pez V, del R\u00edo S, Ben\u00edtez JM, Herrera F (2015) Cost-sensitive linguistic fuzzy rule based classification systems under the MapReduce framework for imbalanced big data. Fuzzy Sets Syst 258:5\u201338","journal-title":"Fuzzy Sets Syst"},{"key":"29_CR5","volume-title":"Web Data Mining. Book","author":"L Bing","year":"2008","unstructured":"Bing L (2008) Web Data Mining. Book. Springer, Berlin Heidelberg New York"},{"issue":"2","key":"29_CR6","first-page":"310","volume":"2","author":"RV Bandakkanavar","year":"2014","unstructured":"Bandakkanavar RV, Ramesh M, Geeta H (2014) A survey on detection of reviews using sentiment classification of methods. IJRITCC 2(2):310\u2013314","journal-title":"IJRITCC"},{"issue":"3","key":"29_CR7","doi-asserted-by":"crossref","first-page":"435","DOI":"10.2307\/25750686","volume":"34","author":"A Abbasi","year":"2010","unstructured":"Abbasi A, Zhang Z, Zimbra D, Chen H, Nunamaker JF Jr (2010) Detecting fake websites: the contribution of statistical learning theory. MIS Q 34(3):435\u2013461","journal-title":"MIS Q"},{"key":"29_CR8","doi-asserted-by":"crossref","unstructured":"Jindal N, Liu B, Lim EP (2010) Finding unusual review patterns using unexpected rules. In: Proceedings of the 19th ACM international conference on Information and knowledge management. (pp. 1549\u20131552). ACM, Toronto, ON, Canada","DOI":"10.1145\/1871437.1871669"},{"key":"29_CR9","first-page":"2488","volume-title":"IJCAI Proceedings-International Joint Conference on Artificial Intelligence","author":"F Li","year":"2011","unstructured":"Li F, Huang M, Yang Y, Zhu X (2011) Learning to identify review spam. In: IJCAI Proceedings-International Joint Conference on Artificial Intelligence, vol 22, No. 3., p 2488"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Mukherjee A, Liu B, Glance N (2012) Spotting fake reviewer groups in consumer reviews. In: Proceedings of the 21st international conference on World Wide Web. (pp. 191\u2013200). ACM, Lyon, France","DOI":"10.1145\/2187836.2187863"},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Shojaee S, Murad MAA, Bin Azman A, Sharef NM, Nadali S (2013) Detecting deceptive reviews using lexical and syntactic features. In: Intelligent Systems Design and Applications (ISDA), 2013 13th International Conference on (pp. 53\u201358). IEEE, Serdang, Malaysia","DOI":"10.1109\/ISDA.2013.6920707"},{"key":"29_CR12","first-page":"497","volume-title":"HLT-NAACL","author":"M Ott","year":"2013","unstructured":"Ott M, Cardie C, Hancock JT (2013) Negative Deceptive Opinion Spam. In: HLT-NAACL., pp 497\u2013501"},{"key":"29_CR13","first-page":"1124","volume-title":"EMNLP","author":"T Qian","year":"2013","unstructured":"Qian T, Liu B (2013) Identifying Multiple Userids of the Same Author. In: EMNLP., pp 1124\u20131135"},{"key":"29_CR14","doi-asserted-by":"crossref","unstructured":"Mukherjee A, Kumar A, Liu B, Wang J, Hsu M, Castellanos M, Ghosh R (2013) Spotting opinion spammers using behavioral footprints. In: Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining (pp. 632\u2013640). Chicago, ACM.","DOI":"10.1145\/2487575.2487580"},{"key":"29_CR15","first-page":"98","volume":"12","author":"S Feng","year":"2012","unstructured":"Feng S, Xing L, Gogar A, Choi Y (2012) Distributional footprints of deceptive product reviews. ICWSM 12:98\u2013105","journal-title":"ICWSM"},{"key":"29_CR16","doi-asserted-by":"crossref","unstructured":"Xie S, Wang G, Lin S, Yu PS (2012) Review spam detection via temporal pattern discovery. In: Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining (pp. 823\u2013831). ACM, Beijing, China","DOI":"10.1145\/2339530.2339662"},{"issue":"4","key":"29_CR17","first-page":"61","volume":"3","author":"G Wang","year":"2012","unstructured":"Wang G, Xie S, Liu B, Yu PS (2012) Identify online store review spammers via social review graph. ACM Transactions on Intelligent Systems and Technology (TIST) 3(4):61","journal-title":"ACM Transactions on Intelligent Systems and Technology (TIST)"},{"key":"29_CR18","doi-asserted-by":"crossref","unstructured":"Wang G, Xie S, Liu B, Yu PS (2011) Review graph based online store review spammer detection. In: Data mining (icdm), 2011 ieee 11th international conference on (pp. 1242\u20131247). IEEE, Vancouver, Canada","DOI":"10.1109\/ICDM.2011.124"},{"key":"29_CR19","doi-asserted-by":"crossref","unstructured":"Morales A, Sun H, Yan X (2013) Synthetic review spamming and defense. In: Proceedings of the 22nd international conference on World Wide Web companion (pp. 155\u2013156). International World Wide Web Conferences Steering Committee, Rio de Janeiro, Brazil","DOI":"10.1145\/2487788.2487864"},{"key":"29_CR20","doi-asserted-by":"crossref","unstructured":"Jindal N, Liu B (2007) Review spam detection. In: Proceedings of the 16th international conference on World Wide Web (pp. 1189\u20131190). ACM, Lyon, France","DOI":"10.1145\/1242572.1242759"},{"key":"29_CR21","doi-asserted-by":"crossref","unstructured":"Jindal N, Liu B (2008) Opinion spam and analysis. In: Proceedings of the 2008 International Conference on Web Search and Data Mining (pp. 219\u2013230). ACM, Stanford, CA","DOI":"10.1145\/1341531.1341560"},{"key":"29_CR22","first-page":"175","volume":"13","author":"G Fei","year":"2013","unstructured":"Fei G, Mukherjee A, Liu B, Hsu M, Castellanos M, Ghosh R (2013) Exploiting Burstiness in reviews for review spammer detection. ICWSM 13:175\u2013184","journal-title":"ICWSM"},{"key":"29_CR23","unstructured":"Mukherjee A, Venkataraman V, Liu B, Glance NS (2013) What yelp fake review filter might be doing? Boston, In ICWSM."},{"key":"29_CR24","volume-title":"An Approach for Detecting Spam in Arabic Opinion Reviews","author":"ASA Hammad","year":"2013","unstructured":"Hammad ASA (2013) An Approach for Detecting Spam in Arabic Opinion Reviews. Doctoral dissertation, Islamic University of Gaza"},{"key":"29_CR25","doi-asserted-by":"crossref","unstructured":"Li J, Ott M, Cardie C, Hovy E (2014) Towards a general rule for identifying deceptive opinion spam. Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, pages 1566\u20131576, Baltimore, Maryland, USA, June 23-25 2014. ACL","DOI":"10.3115\/v1\/P14-1147"},{"key":"29_CR26","unstructured":"Part of Speech Tagging (POS). http:\/\/en.wikipedia.org\/wiki\/Part-of-speech_tagging"},{"key":"29_CR27","doi-asserted-by":"crossref","unstructured":"Mayzlin D, Dover Y, Chevalier JA (2012) Promotional reviews: An empirical investigation of online review manipulation (No. w18340). National Bureau of Economic Research, Nashville, TN","DOI":"10.3386\/w18340"},{"key":"29_CR28","first-page":"1157","volume":"3","author":"I Guyon","year":"2003","unstructured":"Guyon I, Elisseeff A (2003) An introduction to variable and feature selection. J Mach Learn Res 3:1157\u20131182","journal-title":"J Mach Learn Res"},{"key":"29_CR29","volume-title":"The development and psychometric properties of LIWC2007","author":"JW Pennebaker","year":"2007","unstructured":"Pennebaker JW, Chung CK, Ireland M, Gonzales A, Booth RJ (2007) The development and psychometric properties of LIWC2007"},{"key":"29_CR30","first-page":"1041","volume-title":"Proceedings of the 28th International Conference on Machine Learning (ICML-11)","author":"J Eisenstein","year":"2011","unstructured":"Eisenstein J, Ahmed A, Xing EP (2011) Sparse additive generative models of text. In: Proceedings of the 28th International Conference on Machine Learning (ICML-11)., pp 1041\u20131048"},{"issue":"1","key":"29_CR31","doi-asserted-by":"crossref","first-page":"49","DOI":"10.2753\/MIS0742-1222250103","volume":"25","author":"A Abbasi","year":"2008","unstructured":"Abbasi A, Chen H, Nunamaker JF (2008) Stylometric identification in electronic markets: Scalability and robustness. J Manage Inf Syst 25(1):49\u201378","journal-title":"J Manage Inf Syst"},{"key":"29_CR32","volume-title":"Fake review detection: Classification and analysis of real and pseudo reviews","author":"A Mukherjee","year":"2013","unstructured":"Mukherjee A, Venkataraman V, Liu B, Glance N (2013) Fake review detection: Classification and analysis of real and pseudo reviews. Technical Report UIC-CS-2013-03, University of Illinois, Chicago"},{"key":"29_CR33","doi-asserted-by":"crossref","unstructured":"Chapelle O, Sch\u00f6lkopf B, Zien A (2006) Semi-supervised learning. Vol. 2. Cambridge: MIT press.","DOI":"10.7551\/mitpress\/9780262033589.001.0001"},{"key":"29_CR34","doi-asserted-by":"crossref","unstructured":"Blum A, Mitchell T (1998) Combining labeled and unlabeled data with co-training. In: Proceedings of the eleventh annual conference on Computational learning theory (pp. 92\u2013100). ACM, Madison, WI","DOI":"10.1145\/279943.279962"},{"key":"29_CR35","doi-asserted-by":"crossref","unstructured":"Liu B, Dai Y, Li X, Lee WS, Yu PS (2003) Building text classifiers using positive and unlabeled examples. In: Data Mining, 2003. ICDM 2003. Third IEEE International Conference on (pp. 179\u2013186). Melbourne, Florida, IEEE","DOI":"10.1109\/ICDM.2003.1250918"},{"key":"29_CR36","first-page":"38","volume-title":"Proc. of the 4th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis","author":"D Hern\u00e1ndez","year":"2013","unstructured":"Hern\u00e1ndez D, Guzm\u00e1n R, M\u00f3ntes y Gomez M, Rosso P (2013) Using PU-learning to detect deceptive opinion spam. In: Proc. of the 4th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis., pp 38\u201345"},{"key":"29_CR37","doi-asserted-by":"crossref","unstructured":"Lim EP, Nguyen VA, Jindal N, Liu B, Lauw HW (2010) Detecting product review spammers using rating behaviors. In: Proceedings of the 19th ACM international conference on Information and knowledge management (pp. 939\u2013948). ACM, Toronto, CA","DOI":"10.1145\/1871437.1871557"},{"key":"29_CR38","unstructured":"Richter AN, Khoshgoftaar TM, Landset S, Hasanin T. A Multi-Dimensional Comparison of Toolkits for Machine Learning with Big Data. IEEE (in press)"},{"key":"29_CR39","doi-asserted-by":"crossref","unstructured":"Sumbaly R, Kreps J, Shah S (2013) The big data ecosystem at LinkedIn. In: Proceedings of the 2013 ACM SIGMOD International Conference on Management of Data on (pp.1125- 1134). SIGMOD, NY, NY","DOI":"10.1145\/2463676.2463707"},{"key":"29_CR40","unstructured":"Kourtellis N, Morales GDF, Bonchi F, De G, Morales F (2014) Scalable online betweenness centrality in evolving graphs. CoRR, abs\/1401.6981"},{"key":"29_CR41","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/3-540-45014-9_1","volume-title":"Multiple classifier systems","author":"TG Dietterich","year":"2000","unstructured":"Dietterich TG (2000) Ensemble methods in machine learning. In: Multiple classifier systems. Springer, Berlin Heidelberg, pp 1\u201315"},{"issue":"3","key":"29_CR42","doi-asserted-by":"crossref","first-page":"552","DOI":"10.1109\/TSMCA.2010.2084081","volume":"41","author":"TM Khoshgoftaar","year":"2011","unstructured":"Khoshgoftaar TM, Van Hulse J, Napolitano A (2011) Comparing boosting and bagging techniques with noisy and imbalanced data. IEEE Trans Syst Man Cybern A Syst Hum 41(3):552\u2013568","journal-title":"IEEE Trans Syst Man Cybern A Syst Hum"},{"issue":"12","key":"29_CR43","doi-asserted-by":"crossref","first-page":"1513","DOI":"10.1016\/j.datak.2009.08.005","volume":"68","author":"J Hulse Van","year":"2009","unstructured":"Van Hulse J, Khoshgoftaar T (2009) Knowledge discovery from imbalanced and noisy data. Data Knowl Eng 68(12):1513\u20131542","journal-title":"Data Knowl Eng"},{"key":"29_CR44","doi-asserted-by":"crossref","unstructured":"Al Najada H, Zhu X (2014) iSRD: Spam review detection with imbalanced data distributions. In: Information Reuse and Integration (IRI), 2014 IEEE 15th International Conference on (pp. 553\u2013560). IEEE, San Francisco, CA","DOI":"10.1109\/IRI.2014.7051938"}],"container-title":["Journal of Big Data"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-015-0029-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s40537-015-0029-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-015-0029-9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,31]],"date-time":"2019-08-31T02:59:52Z","timestamp":1567220392000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.journalofbigdata.com\/content\/2\/1\/23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,10,5]]},"references-count":44,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2015,12]]}},"alternative-id":["29"],"URL":"https:\/\/doi.org\/10.1186\/s40537-015-0029-9","relation":{},"ISSN":["2196-1115"],"issn-type":[{"value":"2196-1115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,10,5]]},"article-number":"23"}}