Boosting credibility of a Recommender System using Deep Learning Techniques - An Empirical Study

Boosting credibility of a Recommender System using Deep Learning Techniques - An Empirical Study
  IJETT-book-cover           
  
© 2021 by IJETT Journal
Volume-69 Issue-10
Year of Publication : 2021
Authors : R. SujithraKanmani, B. Surendiran
DOI :  10.14445/22315381/IJETT-V69I10P230

How to Cite?

R. SujithraKanmani, B. Surendiran, "Boosting credibility of a Recommender System using Deep Learning Techniques - An Empirical Study," International Journal of Engineering Trends and Technology, vol. 69, no. 10, pp. 235-243, 2021. Crossref, https://doi.org/10.14445/22315381/IJETT-V69I10P230

Abstract
The recommendation system provides the user with their needed item or service by analyzing their preference history. In recent times the location-based recommendation has played a significant role in our everyday life. User interaction towards the internet is based on the social relationships comprising User Generated Content (UGC) like online reviews. A collaborative filtering approach is a popular recommendation framework for making recommendations to a new user based on comparable user content. However, it is vulnerable to Shilling attacks, in which shills put any unethical data into the ratings or comments database in order to modify the recommendations. As a lacking of trust format, the risk of misinformation becomes a research and evaluation concern. This paper proposes a trustworthy recommendation framework using the content features of the Deceptive opinion spam corpus dataset by employing the various deep learning algorithms in predicting the truthfulness of the reviews. Among the inspired models, the proposed hybrid combination of CNN-LSTM involving content feature excels in accuracy and prediction, thereby improving the performance and stability of the recommendation system.

Keywords
User Generated Content (UGC), Shilling attack, Long Short-term Memory (LSTM), Gated Recurrent Unit (GRU), Convolutional Neural Network (CNN), Bidirectional Long Short Term Memory (Bi-LSTM).

Reference
[1] Rajabpour, Neda, et al. Application domain of recommender system: a survey. International Journal of Advanced Studies in Computers, Science and Engineering, 3(2) 2014, doi: http://www.ijascse.org/.
[2] J. Bao, Y. Zheng, D. Wilkie, and M. Mokbel, Recommendations in location-based social networks : A survey Recommendations in location-based social networks : a survey, ACM Transaction on Intelligent systems and technology, July, (2015), doi: 10.1007/s10707-014-0220-8.
[3] V. W. Zheng, Y. Zheng, X. Xie, and Q. Yang, Towards mobile intelligence : Learning from GPS history data for collaborative recommendation, Artif. Intell., 184–185 (202) 17–37, doi: 10.1016/j.artint.2012.02.002.
[4] R. Katarya and O. P. Verma, Effectivecollaborative movie recommender system using asymmetric user similarity and matrix factorization, 2016 Int. Conf. Comput. Commun. Autom., (2016) 71–75, doi: 10.1109/CCAA.2016.7813692.
[5] L. Guo, J. Liang, Y. Zhu, Y. Luo, L. Sun, and X. Zheng, Collaborative filtering recommendation based on trust and emotion, J. Intell. Inf. Syst., 53(1) (2019) 113–135, doi: 10.1007/s10844-018- 0517-4.
[6] M. Si and Q. Li, Shilling attacks against collaborative recommender systems : a review, Artif. Intell. Rev., 53(1) (2020) 291–319, doi: 10.1007/s10462-018-9655-x.
[7] A. P. Sundar, F. Li, X. Zou, T. Gao, and E. D. Russomanno, Understanding shilling attacks and their detection traits: A comprehensive survey, IEEE Access, 8(2020) 171703–171715, doi: 10.1109/ACCESS.2020.3022962.
[8] W. Long, Z. Lu, and L. Cui, Deep learning-based feature engineering for stock price movement prediction, Knowledge-Based Syst., 164 (2019) 163–173, doi: 10.1016/j.knosys.2018.10.034.
[9] Kumar, Lokesh. Predictive Analytics of COVID-19 Pandemic: Statistical Modelling Perspective. Walailak Journal of Science and Technology (WJST), 18(16) (2021) , doi:https://doi.org/10.48048/wjst.2021.15583.
[10] Wiese B., OmlinC. Credit Card Transactions, Fraud Detection, and Machine Learning: Modelling Time with LSTM Recurrent Neural Networks, Innovations in Neural Information Paradigms and Applications. Studies in Computational Intelligence, 247, 231– 268,doi: https://doi.org/10.1007/978-3-642-04003-0_10.
[11] T. Fornaciari and L. Cagnina, Fake opinion detection : how similar are crowdsourced datasets to real data ?, Lang. Resour. Eval., (2020), doi: 10.1007/s10579-020-09486-5.
[12] M. Schuster and K. K. Paliwal, Bidirectional recurrent neural networks, IEEE Trans. Signal Process., 45(11) (1997) 2673–2681, doi: 10.1109/78.650093.
[13] V. Makarenkov, L. Rokach, and B. Shapira, Choosing the right word: Using bidirectional LSTM tagger for writing support systems, Eng. Appl. Artif. Intell., 84 (2019) 1–10, doi: 10.1016/j.engappai.2019.05.003.
[14] Y. Heryadi and H. L. H. S. Warnars, Learning temporal representation of transaction amount for fraudulent transaction recognition using CNN, Stacked LSTM, and CNN-LSTM, 2017 IEEE Int. Conf. Cybern. Comput. Intell. Cybern. 2017 - Proc., 2017(2018) 84–89, doi: 10.1109/CYBERNETICSCOM.2017.8311689.
[15] K. Vivekanandan and N. Praveena, Hybrid convolutional neural network (CNN) and long-short term memory (LSTM) based deep learning model for detecting shilling attack in the social-aware network, J. Ambient Intell. Humaniz. Comput., 12(1) (2021) 1197– 1210, doi: 10.1007/s12652-020-02164-y.
[16] M. Rhanoui, M. Mikram, S. Yousfi, and S. Barzali, A CNNBiLSTM Model for Document-Level Sentiment Analysis, Mach. Learn. Knowl. Extr., 1(3) (2019) 832–847, doi: 10.3390/make1030048.
[17] L. Zhang and F. Xiang, Relation Classi fi cation via BiLSTM-CNN, Data Mining and Big data no. 10 (2018) 373–382, doi: 10.1007/978- 3-319-93803-5.
[18] Okura, Shumpei, Yukihiro Tagami, Shingo Ono, and Akira Tajima. Embedding-based news recommendation for millions of users. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, (2017) 1933-1942, doi: https://doi.org/10.1145/3097983.3098108
[19] B. Liu, Y. Zhou, and W. Sun, Character-level text classification via convolutional neural network and gated recurrent unit, Int. J. Mach. Learn. Cybern., 11(8) (2020) 1939–1949, doi: 10.1007/s13042-020- 01084-9.
[20] S. Y. Yerima, M. K. Alzaylaee, A. Shajan, andP.Vinod, Deep learning techniques for android botnet detection, Electroics., 10(4) (2021) 1–17, doi: 10.3390/electronics10040519.
[21] Anjani KumarVerma, Veer Sain Dixit, Security Based Recommender System Against Profile Injection Attack. International Journal of Engineering Trends and Technology, 69(3) 219-228.doi: 10.14445/22315381/IJETT-V69I3P233.
[22] Kaushik, Shaivya, and Pradeep Tomar. Evaluation of Similarity Functions by using User based Collaborative Filtering approach in Recommendation Systems. IJETT, (2015) 194-200.
[23] Londt, Trevor, Xiaoying Gao, and Peter Andreae., Evolving Character-level DenseNet architectures using genetic programming. In International Conference on the Applications of Evolutionary Computation (Part of EvoStar), (2021) 665-680. Springer, Cham, doi: https://doi.org/10.1007/978-3-030-72699-7_42.
[24] Ruiz J., Mahmud M., Modasshir M., Shamim Kaiser M., Alzheimer’s Disease Neuroimaging Initiative, 3D DenseNet Ensemble in 4-Way Classification of Alzheimer’s Disease. In: Mahmud M., Vassanelli S., Kaiser M.S., Zhong N. (eds) Brain Informatics. BI 2020. Lecture Notes in Computer Science, 12241 (2020). Springer, Cham.doi:https://doi.org/10.1007/978-3-030- 59277-6_8.
[25] Yu, Su-Gyeong, Kun Ha Suh, and EuiChul Lee. Face Spoofing Detection Using DenseNet. In International Conference on Intelligent Human Computer Interaction, (2020) 229-238, doi: https://doi.org/10.1007/978-3-030-68452-5_24.