{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:16:46Z","timestamp":1780636606538,"version":"3.54.1"},"reference-count":36,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2019,7,17]],"date-time":"2019-07-17T00:00:00Z","timestamp":1563321600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>Consumers\u2019 purchase behavior increasingly relies on online reviews. Accordingly, there are more and more deceptive reviews which are harmful to customers. Existing methods to detect spam reviews mainly take the problem as a general text classification task, but they ignore the important features of spam reviews. In this paper, we propose a novel model, which splits a review into three parts: first sentence, middle context, and last sentence, based on the discovery that the first and last sentence express stronger emotion than the middle context. Then, the model uses four independent bidirectional long-short term memory (LSTM) models to encode the beginning, middle, end of a review and the whole review into four document representations. After that, the four representations are integrated into one document representation by a self-attention mechanism layer and an attention mechanism layer. Based on three domain datasets, the results of in-domain and mix-domain experiments show that our proposed method performs better than the compared methods.<\/jats:p>","DOI":"10.3390\/info10070243","type":"journal-article","created":{"date-parts":[[2019,7,18]],"date-time":"2019-07-18T03:11:42Z","timestamp":1563419502000},"page":"243","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":28,"title":["A Review Structure Based Ensemble Model for Deceptive Review Spam"],"prefix":"10.3390","volume":"10","author":[{"given":"Zhi-Yuan","family":"Zeng","sequence":"first","affiliation":[{"name":"School of Software, Nanchang University, Nanchang 33047, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1649-9531","authenticated-orcid":false,"given":"Jyun-Jie","family":"Lin","sequence":"additional","affiliation":[{"name":"National Taipei University of Business, Jinan Rd., Zhongzheng District, Taipei 10051, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mu-Sheng","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Software, Jiangxi university of Science and Technology, Nanchang 330013, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng-Hui","family":"Chen","sequence":"additional","affiliation":[{"name":"National Taipei University of Business, Jinan Rd., Zhongzheng District, Taipei 10051, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan-Qi","family":"Lan","sequence":"additional","affiliation":[{"name":"School of Software, Nanchang University, Nanchang 33047, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun-Lin","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Software, Nanchang University, Nanchang 33047, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2019,7,17]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Jindal, N., and Liu, B. (2008, January 11\u201312). Opinion spam and analysis. Proceedings of the 2008 International Conference on Web Search and Data Mining (WSDM \u201908), Palo Alto, CA, USA.","DOI":"10.1145\/1341531.1341560"},{"key":"ref_2","unstructured":"Ott, M., Choi, Y., Cardie, C., and Hancock, J.T. (2011, January 19\u201324). Finding Deceptive Opinion Spam by Any Stretch of the Imagination. Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (HLT \u201911), Portland, OR, USA."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Ott, M., Cardie, C., and Hancock, J.T. (2012, January 16\u201320). Estimating the prevalence of deception in online review communities. Proceedings of the 21st international conference on World Wide Web (WWW \u201912), Lyon, France.","DOI":"10.1145\/2187836.2187864"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Li, J., Ott, M., Cardie, C., and Hovy, E.H. (2014, January 23\u201325). Towards a General Rule for Identifying Deceptive Opinion Spam. Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, Baltimore, MD, USA.","DOI":"10.3115\/v1\/P14-1147"},{"key":"ref_5","unstructured":"Li, J., Cardie, C., and Li, S. (2013, January 4\u20139). Topics pam: A topic-model based approach for spam detection. Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, Sofia, Bulgaria."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1016\/j.neucom.2016.10.080","article-title":"Document representation and feature combination for deceptive spam review detection","volume":"254","author":"Li","year":"2017","journal-title":"Neurocomputing"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1016\/j.ins.2017.01.015","article-title":"Neural networks for deceptive opinion spam detection: An empirical study","volume":"385\u2013386","author":"Ren","year":"2017","journal-title":"Inf. Sci."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1016\/j.sysconle.2018.10.001","article-title":"Resilient consensus of switched multi-agent systems","volume":"122","author":"Shang","year":"2018","journal-title":"Syst. Control Lett."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Shang, Y. (2018). Resilient Multiscale Coordination Control against Adversarial Nodes. Energies, 11.","DOI":"10.3390\/en11071844"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"244","DOI":"10.1016\/j.chaos.2018.03.037","article-title":"Hybrid consensus for averager\u2013copier\u2013voter networks with non-rational agents","volume":"110","author":"Shang","year":"2018","journal-title":"Chaos Solit. Fract."},{"key":"ref_11","unstructured":"Feng, S., Banerjee, R., and Choi, Y. (2014, January 22). Syntactic stylometry for deception detection. Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, Baltimore, MD, USA."},{"key":"ref_12","unstructured":"Xu, Q., and Zhao, H. (2012, January 8\u201315). Using deep linguistic features for finding deceptive opinion spam. Proceedings of the COLING, Mumbai, India."},{"key":"ref_13","unstructured":"Banerjee, S., and Chua, A.Y. (2014, January 22). A linguistic framework to distinguish between genuine and deceptive online reviews. Proceedings of the International Conference on Internet Computing and Web Services, Baltimore, MD, USA."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Fusilier, D.H., Montesygomez, M., Rosso, P., and Cabrera, R.G. (2015, January 14\u201320). Detection of opinion spam with character n-grams. Proceedings of the Conference on Intelligent Text Processing and Computational Linguistics, Cairo, Egypt.","DOI":"10.1007\/978-3-319-18117-2_21"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1016\/j.ipm.2014.11.001","article-title":"Detecting positive and negative deceptive opinions using PU-learning","volume":"51","author":"Fusilier","year":"2015","journal-title":"Inf. Process. Manag."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Hai, Z., Zhao, P., Cheng, P., Yang, P., Li, X., and Li, G. (2016, January 1\u20135). Deceptive Review Spam Detection via Exploiting Task Relatedness and Unlabeled Data. Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, Austin, TX, USA.","DOI":"10.18653\/v1\/D16-1187"},{"key":"ref_17","unstructured":"Feng, S., Xing, L., Gogar, A., and Choi, Y. (2012, January 4\u20137). Distributional Footprints of Deceptive Product Reviews. Proceedings of the International Conference on Weblogs and Social Media, Dublin, Ireland."},{"key":"ref_18","unstructured":"Liu, Y., and Pang, B. (2019). Spam Detection based on Annotation Extension and Neural Networks. Comp. Inf. Sci., Available online: https:\/\/pdfs.semanticscholar.org\/a312\/7f6c118a6e29be12679cefda14a363f9028e.pdf."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Sun, C., Du, Q., and Tian, G. (2016). Exploiting Product Related Review Features for Fake Review Detection. Math. Probl. Eng., 1\u20137.","DOI":"10.1155\/2016\/4935792"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1007\/BF00058655","article-title":"Bagging predictors","volume":"24","author":"Breiman","year":"1996","journal-title":"Mach. Learn."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1007\/BF00116037","article-title":"The strength of weak learnability","volume":"5","author":"Schapire","year":"1990","journal-title":"Mach. Learn."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_23","unstructured":"K\u00e9gl, B. (2013). The return of AdaBoost. MH: Multi-class Hamming trees. arXiv."},{"key":"ref_24","unstructured":"Perrone, M.P., and Cooper, L.N. (2019, June 03). When Networks Disagree: Ensemble Methods for Hybrid Neural Networks. Available online: https:\/\/pdfs.semanticscholar.org\/5956\/40253ffdfd12e04ac57bd78753f936a7cfad.pdf?_ga=2.149320566.1196925254.1559288762-513896128.1544690129."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"993","DOI":"10.1109\/34.58871","article-title":"Neural network ensembles","volume":"10","author":"Hansen","year":"1990","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1162\/neco.1989.1.2.270","article-title":"A learning algorithm for continually running fully recurrent neural networks","volume":"1","author":"Williams","year":"1989","journal-title":"Neural Comput."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"602","DOI":"10.1016\/j.neunet.2005.06.042","article-title":"Framewise phoneme classification with bidirectional LSTM and other neural network architectures","volume":"18","author":"Graves","year":"2005","journal-title":"Neural Netw."},{"key":"ref_29","first-page":"1137","article-title":"A neural probabilistic language model","volume":"3","author":"Bengio","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1162\/tacl_a_00051","article-title":"Enriching Word Vectors with Subword Information","volume":"5","author":"Bojanowski","year":"2017","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"ref_31","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., and Polosukhin, I. (2017, January 4\u20139). Attention is All You Need. Proceedings of the 2017 Neural Information Processing Systems (NIPS), Long Beach, CA, USA."},{"key":"ref_32","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref_33","unstructured":"Gal, Y., and Ghahramani, Z. (2016, January 4\u20139). A theoretically grounded application of dropout in recurrent neural networks. Proceedings of the 30th Conference on Neural Information Processing Systems (NIPS 2016), Barcelona, Spain."},{"key":"ref_34","unstructured":"Palatucci, M., Pomerleau, D.A., Hinton, G.E., and Mitchell, T.M. (2009, January 7\u201310). Zero-shot Learning with Semantic Output Codes. Proceedings of the 22nd International Conference on Neural Information Processing Systems (NIPS\u201909), Vancouver, BC, Canada."},{"key":"ref_35","unstructured":"Ganin, Y., and Lempitsky, V. (2015, January 6\u201311). Unsupervised domain adaptation by backpropagation. Proceedings of the International Conference on Machine Learning, Lille, France."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Peng, M., Zhang, Q., Jiang, Y., and Huang, X. (2018, January 15\u201320). Cross-Domain Sentiment Classification with Target Domain Specific Information. Proceedings of the Meeting of the Association for Computational Linguistics, Melbourne, Australia.","DOI":"10.18653\/v1\/P18-1233"}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/10\/7\/243\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T13:06:45Z","timestamp":1760188005000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/10\/7\/243"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7,17]]},"references-count":36,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2019,7]]}},"alternative-id":["info10070243"],"URL":"https:\/\/doi.org\/10.3390\/info10070243","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,7,17]]}}}