Journal of Scientific and Industrial Research

Open Access Open Access  Restricted Access Subscription Access

Deep Learning Hybrid Approaches to Detect Fake Reviews and Ratings


Affiliations
1 Department of C.S.E.Gitam IT, Visakhapatnam, 530 045, Andhra Pradesh, India
 

Nowadays, online reviews and ratings are the most valuable source of word-of-mouth, voice-of-customer, and feedback, also customers can make purchasing decisions on what to buy, where to buy, and what to select. Genuine online reviews are becoming popular, but unfortunately, we have an issue that might only sometimes be unbiased or accurate. Because most of the reviews are fake reviews and ratings, these could mislead innocent customers and highly influence customers' purchasing decisions in the wrong manner. This paper's primary goal is to accurately detect fake reviews and what is the main difference between them. The secondary goal is to detect fake ratings and actual ratings-based reviews across the online platform, especially Amazon datasets. The Paper proposes two novel deep-learning Hybrid techniques: CNN-LSTM for detecting fake online reviews, and LSTM-RNN for detecting fake ratings in the e-commerce domain. Both Hybrid models can outperform and achieve better performance with the most advanced word embedding techniques, Glove, and One hot encoding techniques. As per the experimental results, the first technique efficiently detects fake online reviews with the highest prediction accuracy. The second hybrid model is better than the existing models that detect fake online ratings with the most excellent precision of 93.8%. The experimental research efficiently revealed that the CNN-LSTM and LSTM-RNN methods are more efficient and practicable and might be better suited for optimal results and maximizing the efficiency of fake online review detection.

Keywords

CNN-LSTM, Glove, LSTM-RNN, One Hot Encoding.
User
Notifications
Font Size

  • He L, Wang X, Chen H & Xu G, Online spam review detection: a survey of the literature, Human-Centric Intell Syst, 2 (2022) 14–30, DOI: 10.1007/s44230-022-00001-3.

  • Halder S, Dutta S, Banerjee P, Mukherjee U, Mehta A & Ganguli R, A survey on online spam review detection, in Emerg Techonol Data Min Inf Secur, 1300 (2021) 717–724, DOI:10.1007/978-981-33-4367-2_68.

  • Ren Y & Zhang Y, Deceptive opinion spam detection using neural network, in Proc COLING 2016, the 26th Int Conf Comput Linguist: Technical Papers, (Osaka, Japan), 2016, 140–150, DOI:10.1007/s10489-022-03427-1.

  • Desale K S, Shinde S & Magar N A, Fake review detection with concept drift in the data: a survey, in Proc Seventh Int Cong Inf Commun Technol, Lect Notes Netw Syst, vol 448, edited by X S Yang, S Sherratt, N Dey & A Joshi (Springer, Singapore) (2022) 719–726, https://doi.org/10.1007/978-981-19-1610-6_63.

  • Jian Y, Chen X & Wang H, Fake restaurant review detection using deep neural networks with hybrid feature fusion method, in Database Systems for Advanced Applications, DASFAA 2022, Lecture Notes in Computer Science, vol 13247, edited by, et al. (Springer, Cham) 2022, 133–148, https://doi.org/10.1007/978-3-031-00129-1_9.

  • Rehman A U, Malik A K, Raza B & Waqar A, A Hybrid CNN-LSTM model for improving the accuracy of movie reviews sentiment analysis, Multimed Tools Appl, 78(6) (2019), 26597–26613, DOI:10.1007/s11042-019-07788-7.

  • Habbat N, Anoun H & Hassouni L, LSTM-CNN deep learning model for french online product reviews classification, in Advanced Technologies for Humanity, ICATH 2021, Lecture Notes on Data Engineering and Communications Technologies, vol 110, edited by R Saidi, B El Bhiri, Y Maleh, A Mosallam & M Essaaidi (Springer, Cham) 2022, 228–240, https://doi.org/10.1007/978-3-030-94188-8_22.

  • Singh M, Jakhar A K & Pandey S, Sentiment analysis on the impact of coronavirus in social life using the BERT model, Soc Netw Anal Min, 11 (2021) 1–11, DOI:10.1007/s13278-021-00737-7.

  • Tesfagergish S G, Damaševičius R & Kapočiūtė-Dzikienė J, Deep fake recognition in tweets using text augmentation, word embeddings and deep learning, in Computational Science and Its Applications – ICCSA 2021. ICCSA 2021, Lecture Notes in Computer Science, vol 12954, edited by et al. (Springer, Cham) 2021, 523–538, https://doi.org/10.1007/978-3-030-86979-3_37.

  • Sagnika S, Mishra B S P & Meher S K, An attention-based CNN-LSTM model for subjectivity detection in opinion-mining, Neural Comput Appl, 33 (2021) 17425–17438, https://doi.org/10.1007/s00521-021-06328-5.

  • Rehman U A, Malik A K, Basit R & Waqar A, A hybrid CNN-LSTM model for improving accuracy of movie reviews sentiment analysis, Multimed Tools Appl, 78 (2019) 26597–26613, https://doi.org/10.1007/s11042-019-07788-7.

  • Alzahrani M E, Aldhyani T H H, Alsubari S N, Althobaiti M M & Fahad A, Developing an intelligent system with deep learning algorithms for sentiment analysis of e-commerce product reviews, Comput Intell Neurosci, 2 (2022) 1–10, DOI:10.1155/2022/3840071.

  • Jiang C, Zhang X & Jin A, Detecting online fake reviews via hierarchical neural networks and multivariate features, in Neural Information Processing, ICONIP 2020, Lecture Notes in Computer Science, vol 12532, edited by H Yang, K Pasupa, A CS Leung, J T Kwok, J H Chan & King I (Springer, Cham), 2020, 730–742, https://doi.org/10.1007/978-3-030-63830-6_61.

  • Alton Y K C & Xiaoyu C, Online helpful Lies: An empirical study of helpfulness in fake and authentic online reviews, in Information for a Better World: Shaping the Global Future, iConference 2022, Lecture Notes in Computer Science, vol 13192, edited by M Smits (Springer, Cham) 2022, 91–99, DOI:10.1007/978-3-030-96957-8_10.

  • Deshai N & Bhaskara Rao B, A detection of unfairness online reviews using deep learning, J Theor Appl Inf Technol, 100(13) (2022) 4738–4779.

  • Deshai N, Sekhar B V D S, Prasad Reddy P V G D & Chakravarthy V V S S S, Processing real-world datasets using big data hadoop tools, J Sci Ind Res, 79(7) (2020) 631–638.

  • Srivastava A, Gupta A & Anand R, optimized smart system for transportation using RFID technology, Math Eng Sci Aerosp, 12(4) (2021) 953–965.

  • Raghavan R, Verma D C & Pandey D, Optimized building extraction from high-resolution satellite imagery using deep learning, Multimed Tools Appl, 81(2) (2022) 42309–42323, DOI:10.1007/s11042-022-13493.

  • Bakshi G, Shukla R, Yadav V, Dahiya A, Anand R, Sindhwani N & Singh H, An optimized approach for feature extraction in multi-relational statistical learning, J Sci Ind Res, 80(6) (2021) 537–542, DOI: 10.56042/jsir.v80i6.43632.

  • Sule O B, Ipek K & Sachin K M, Detecting fake reviews through topic modeling, J Bus Res, 149 (2022) 884–900, DOI: 10.1016/j.jbusres.2022.05.081.


Abstract Views: 54

PDF Views: 43




  • Deep Learning Hybrid Approaches to Detect Fake Reviews and Ratings

Abstract Views: 54  |  PDF Views: 43

Authors

N Deshai
Department of C.S.E.Gitam IT, Visakhapatnam, 530 045, Andhra Pradesh, India
B Bhaskara Rao
Department of C.S.E.Gitam IT, Visakhapatnam, 530 045, Andhra Pradesh, India

Abstract


Nowadays, online reviews and ratings are the most valuable source of word-of-mouth, voice-of-customer, and feedback, also customers can make purchasing decisions on what to buy, where to buy, and what to select. Genuine online reviews are becoming popular, but unfortunately, we have an issue that might only sometimes be unbiased or accurate. Because most of the reviews are fake reviews and ratings, these could mislead innocent customers and highly influence customers' purchasing decisions in the wrong manner. This paper's primary goal is to accurately detect fake reviews and what is the main difference between them. The secondary goal is to detect fake ratings and actual ratings-based reviews across the online platform, especially Amazon datasets. The Paper proposes two novel deep-learning Hybrid techniques: CNN-LSTM for detecting fake online reviews, and LSTM-RNN for detecting fake ratings in the e-commerce domain. Both Hybrid models can outperform and achieve better performance with the most advanced word embedding techniques, Glove, and One hot encoding techniques. As per the experimental results, the first technique efficiently detects fake online reviews with the highest prediction accuracy. The second hybrid model is better than the existing models that detect fake online ratings with the most excellent precision of 93.8%. The experimental research efficiently revealed that the CNN-LSTM and LSTM-RNN methods are more efficient and practicable and might be better suited for optimal results and maximizing the efficiency of fake online review detection.

Keywords


CNN-LSTM, Glove, LSTM-RNN, One Hot Encoding.

References