Online Reviews & Ratings Inter-contradiction based Product’s Quality-Prediction through Hybrid Neural Network

Kemal Polat

1. Department of Computer Science, COMSATS University Islamabad, Vehari Campus, Vehari 61100, Pakistan

2. Department of Computational Science & Engineering, National University of Sciences and Technology, Islamabad.

3. College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China

4. Department of Electrical and Electronics Engineering, Bolu Abant Izzet Baysal University, Bolu 14280, Turkey

*Corresponding Author: [email protected]

With the explosive growth of web usage, people feel comfort to use internet for their personal work such as shopping, sharing information etc. People are more interested in “what other thinks” so the comments and reviews on any online product, movie has huge effect on its earning. Sentiment analysis help people to judge quality by analyzing the reviews. In this era where everyone is so busy in their routine work, it feels like very difficult and time consuming task to check all available reviews on a product. As reviews on a product can be written by anyone so their certainty can be doubtful for example people can give fake reviews just for enjoyment. Another problem with reviews is that contradiction which exists between ratings and reviews of a product for example a person gives 5 star to a product but write a lengthy list of problem exists in that product. To deals with this problem, we are introducing a methodology that finds out contradiction of reviews and ratings of a product then finds out the actual score/quality of product which can save people’s time to read all the reviews or clear their confusion if they stuck between whether to trust on ratings or reviews.  In this research we used CNN Hybrid model which gives 97.5% accuracy which is better than previous models. Dataset is collected from amzon.com. We have also applied CNN Hybrid model on different training and testing dataset ratio in both cases i.e. bigger and smaller dataset. We evaluate CNN hybrid model on both smaller and bigger dataset and experimental results conclude that increasing dataset will increase accuracy of CNN Hybrid Model.

CNN Hybrid Model, Contradiction, Online Ratings, Online Reviews, Product Quality, Sentiment Analysis

Nashit Ali, Anum Fatima, Hureeza Shahzadi, Nasrullah Khan, Kemal Polat (2021). Online Reviews & Ratings Inter-contradiction based Product’s Quality-Prediction through Hybrid Neural Network. Journal of the Institute of Electronics and Computer, 3, 24-52. https://doi.org/10.33969/JIEC.2021.31003.

[1] K. R. Scherer, "Vocal communication of emotion," A review of research paradigms, p. 227–256, 2003. 

[2] A. H. ,. H. K. Walaa Medhat, "Sentiment analysis algorithms and applications:A survey," Ain Shams Engineering Journal, vol. 5, 2014. 

[3] F. C. J. C. Orestes Appel, "Main Concepts, State of the Art and Future Research Questions in Sentiment Analysis," Acta Polytechnica Hungarica, vol. 12, no. 3, 2015. 

[4] M. H. a. B. Liu, "Mining and Summarizing Customer Reviews," ACM SIGKDD, pp. 22-25, 2004. 

[5] R. Feldman, "Techniques and Applications for Sentiment Analysis," Communications of the ACM, vol. 56, no. 4, pp. 82-89, 2013. 

[6] S. G. a. A. S. A. Weichselbraun, "Extracting and Grounding Contextualized Sentiment Lexicons," IEEE Intelligent Systems, vol. 28, no. 2, pp. 39-46, 2013. 

[7] B. Liu., "Sentiment analysis tutorial," AAAI, 2011. 

[8] R. Dale, "Classical Approaches to Natural Language Processing," in Natural Language Processing , 2010, pp. 3-7.

[9] L. S. R. G. R. M. A. M. A. A.-G. GHULAM MUJTABA, "Email Classification Research Trends: Review and Open Issues," Digital Object Identifier, 2017. 

[10] E. I. E. a. A. Gherbi, "Unfair Reviews Detection on Amazon Reviews using Sentiment Analysis with Supervised Learning Techniques," Journal of Computer Science, 2018. 

[11] L. I. S. Sasikala P, "Sentiment Analysis and Prediction of Online Reviews with Empty Ratings," International Journal of Applied Engineering Research, vol. 13, no. 14, pp. 11525-11531, 2018. 

[12] G. Rao, "Detection of Fraud Apps using Sentiment Analysis," International Journal of Innovative Science and Research Technology, vol. 3, no. 5, pp. 91-94, 2018. 

[13] D. E. ,. A. S. E. Laila Abd-Elhamid, "Arabic Feature-Based Level Sentiment Analysis Using Lexicon-Based Approach," Journal of Fundamental and Applied science, vol. 10, no. 4, pp. 143-148, 2018. 

[14] P. R. João Guerreiroa, "How to predict explicit recommendations in online reviews using text mining and sentiment analysis," Journal of Hospitality and Tourism Management, 10 July 2019. 

[15] K. A. Ahlam Alrehili, "Sentiment Analysis of Customer Reviews Using Ensemble Method," in 2019 International Conference on Computer and Information Sciences, 2019. 

[16] I. U. W. J. N. A. Jahanzeb Jabbar, "Real-time Sentiment Analysis On E-Commerce Application," in Proceedings of the 2019 IEEE 16th International Conference on Networking, Sensing and Control,, China, May 2019. 

[17] J. Y. L. L. D. S. Donghang Pan, "Deep neural network-based classification model for Sentiment Analysis," IEEE, 2019. 

[18] M. T. C. O. Reshmi Gopalakrishna Pillai, "Detection of Stress and Relaxation Magnitudes for Tweets," The Sixth International Workshop on Natural Language Processing for Social Media, pp. 23-27, 2018. 

[19] S. A. H. T. N. O. W. A.-S. M. A.-b. Ahmed Al-Saffar, "Malay sentiment analysis based on combined classification approaches and Senti-lexicon algorithm," PLoS ONE, vol. 13, no. 4, 2018. 

[20] A. A. a. S. W. Puspita Kencana Sari, "Measuring e-Commerce service quality from online customer review using sentiment analysis," in IOP Publishing International Conference on Data and Information Science, Indonesia, 2018. 

[21] Y.-J. Park, "Predicting the Helpfulness of Online Customer Reviews across Different Product Types," Sustainability, vol. 10, 2018. 

[22] A. T. Shabeeba T, "Rating Prediction using review texts based on Sentiment Analysis," International Journal of Innovative Research in Science, Engineering and Technology, vol. 7, no. 5, pp. 4714-4718, 2018. 

[23] X. Z. a. Y. Ohsawa, "Sentiment Analysis on the Online Reviews Based on Hidden Markov Model," Journal of Advances in Information Technology, vol. 9, no. 2, pp. 33-38, 2018. 

[24] S. S. B. B. G. G. Swati Redhu, "Sentiment Analysis Using Text Mining: A Review," International Journal on Data Science and Technology, vol. 4, no. 2, pp. 49-53, 2018. 

[25] M. K. a. Ali, "Sentiment Analysis of Pharmaceutical Products Evaluation Based on Customer Review Mining," Journal of Computer Science & Systems Biology, vol. 11, no. 3, pp. 190-194, 2018. 

[26] I. S. F. A. Xiangfeng Dai, "A Framework for Automated Rating of Online Reviews Against the Underlying Topics," in ACMSE, USA, 2017. 

[27] H.-R. Y. a. H.-S. H. Ha-Na Kang, "A Study of Analyzing on Online Game Reviews using a Data Mining Approach: STEAM Community Data," International Journal of Innovation, Management and Technology, vol. 8, no. 2, pp. 90-94, 2017. 

[28] D. G. B. J. B. S. S.-F. C. M. P. Mohammad Soleymani, "A Survey of Multimodal Sentiment Analysis," Image and Vision Computing, 2017. 

[29] V. Dr.B.Radha, "A Survey on Research Issues in Opinion Mining," International Journal of Innovative Research in Computer and Communication Engineering, vol. 5, no. 2, pp. 1849-1853, 2017. 

[30] M. S. A. Sahare, "A Survey Paper on Opinion Mining and Sentiment Analysis," IJARIIE, vol. 3, no. 2, pp. 5075-5078, 2017. 

[31] P. D. S. M. C. M. a. V. Asha S Manek, "Aspect term extraction for sentiment analysis in large movie reviews using Gini Index feature selection method and SVM classifier," World Wide Web, vol. 20, p. 135–154, 2017. 

[32] A. G. Elshrif Elmurngi, "Detecting Fake Review through Sentiment Analysis Using Machine Learning techniques," in The Sixth International Conference on Data Analytics, 2017. 

[33] D. R. T. a. D. R. P. Surya Prakash Sharma, "Opinion Mining and Sentiment Analysis on Customer Review Documents- A Survey," International Journal of Advanced Research in Computer and Communication Engineering, vol. 6, no. 2, pp. 156-159, 2017. 

[34] G. D. a. A. R. Shilpi Chawla, "Product Opinion Mining Using Sentiment Analysis on Smartphone Reviews," in 6th International Conference on Reliability, Infocom Technologies and Optimization (ICRITO, India, 2017. 

[35] V. V. J. V. a. N. D. B. Vaishnavi, "Sentiment Analysis in Online Hotel Booking," International Journal of Engineering Science and Computing,, vol. 7, no. 4, pp. 10725-10728, 2017. 

[36] D. U. R. Babu, "Sentiment Analysis of Reviews for E-Shopping Websites," International Journal Of Engineering And Computer Science, vol. 6, no. 1, pp. 19965-19968, 2017. 

[37] K. T. S. E. Raheesa Safrin, "SENTIMENT ANALYSIS ON ONLINE PRODUCT REVIEW," International Research Journal of Engineering and Technology, vol. 4, no. 4, pp. 2381-2388, 2017. 

[38] V. a. G. S. Sodhi, "Sentiment Mining of Online Reviews Using Machine Learning Algorithms," IJEDR, vol. 5, no. 2, pp. 1321-1334, 2017. 

[39] S. P. S. a. R. S. Mohan Kamal Hassan, "Sentimental analysis of Amazon reviews using naïve bayes on laptop products with MongoDB and R," in IOP Conf. Series: Materials Science and Engineering, 2017. 

[40] D. S.Muthukumaran, "Text Analysis for Product Reviews for Sentiment Analysis using NLP Methods," International Journal of Engineering Trends and Technology (IJETT), vol. 47, no. 8, pp. 474-480, 2017. 

[41] N. M. M. A. A. M. a. N. M. S. Harnani Mat Zin, "The effects of pre-processing strategies in sentiment analysis of online movie reviews," in AIP Conf. The 2nd International Conference on Applied Science and Technology, 2017. 

[42] D. M. E.-D. M. Hussein, "A survey on sentiment analysis challenges," Journal of King Saud University – Engineering Sciences, 2016. 

[43] J. D. P. William J. Amadio, "COMPETITIVE ANALYSIS OF ONLINE REVIEWS USING EXPLORATORY TEXT MINING," Tourism and Hospitality Management, vol. 22, no. 2, pp. 193-210, 2016. 

[44] M. Sodanil, "Multi-Language Sentiment Analysis for Hotel Reviews," in MATEC Web of Conferences ICMIE, 2016. 

[45] H. M. Z. a. S. N. Nurfadhlina Mohd Sharef, "Overview and Future Opportunities of Sentiment Analysis Approaches for Big Data," Journal of Computer Sciences, vol. 12, no. 3, pp. 153-168, 2016. 

[46] S. C. A. G. Devika M D, "Sentiment Analysis:A Comparative Study On Different Approaches," Procedia Computer Science, vol. 87, p. 44 – 49, 2016. 

[47] A. S. Gurneet Kaur, " Sentimental Analysis of Flipkart reviews using Naïve Bayes and Decision Tree algorithm," International Journal of Advanced Research in Computer Engineering & Technology (IJARCET), vol. 5, no. 1, pp. 148-153, 2016. 

[48] R. J. S. a. P. Ajitha, "Survey of Product Reviews using Sentiment Analysis," Indian Journal of Science and Technology, vol. 9, no. 21, 2016. 

[49] A. P. H. C. K. Ga. Aashutosh Bhatt, "Amazon Review Classification and Sentiment Analysis," (IJCSIT) International Journal of Computer Science and Information Technologies, vol. 6, no. 6, pp. 5107-5110, 2015. 

[50] A. A. S. K. R. Abinash Tripathy, "Classification of Sentimental Reviews Using Machine Learning Techniques," Procedia Computer Science, vol. 57, p. 821 – 829, 2015. 

[51] H. M. M. O. I. Doaa Mohey El-Din, "Online Paper Review Analysis," (IJACSA) International Journal of Advanced Computer Science and Applications, vol. 6, no. 9, pp. 220-229, 2015. 

[52] D. S. K. Jeevanandam Jotheeswaran, "Sentiment Analysis: A Survey of Current Research and Techniques," International Journal of Innovative Research in Computer and Communication Engineering, vol. 3, no. 5, pp. 3749-3757, 2015. 

[53] S. K. Yadav, "Sentiment Analysis and Classification: A Survey," International Journal of Advance Research in Computer Science and Management Studies, vol. 3, no. 3, pp. 113-121, 2015. 

[54] X. F. a. J. Zhan, "Sentiment analysis using product review data," Journal of Big Data, vol. 2, no. 5, 2015. 

[55] M. X. D. Z. B. M. Zhijun Yan, "A Context-Dependent Sentiment Analysis of Online Product Reviews based on Dependency Relationships," in Thirty Fifth International Conference on Information Systems, Auckland, 2014. 

[56] S. W. W. H. L. C. L. J. Liu Lizhen, "A Novel Feature-based Method for Sentiment Analysis of Chinese Product Reviews," China Communications, pp. 154-164, 2014. 

[57] N. Nehra, "A SURVEY ON SENTIMENT ANALYSIS OF MOVIE REVIEWS," INTERNATIONAL JOURNAL OF INNOVATIVE RESEARCH IN TECHNOLOGY, vol. 1, no. 7, pp. 36-40, 2014. 

[58] J. Yadav, "A Survey on Sentiment Classification of Movie Reviews," International Journal of Engineering Development and Research, vol. 3, no. 1, pp. 340-343, 2014. 

[59] Q. P. a. M. Zhong, "Detecting Spam Review through Sentiment Analysis," JOURNAL OF SOFTWARE, vol. 9, no. 8, pp. 2065-2071, 2014. 

[60] L. I. S. Sasikala P, "Sentiment Analysis of Online Food Reviews using Customer Ratings," International Journal of Pure and Applied Mathematics, vol. 119, no. 15, pp. 3509-3514, 2018. 

[61] K. W. a. X. Wan, "Sentiment Analysis of Peer Review Texts for Scholarly Papers," Association for Computing Machinery., 2018. 

[62] S. T. A. J. A. F. Kunal Varshney, "Sentiment Analysis of Application Reviews on Play store," International Journal for Research in Applied Science & Engineering Technology (IJRASET), vol. 6, no. 3, 2018. 

[63] A. K. M. B. R. W. A. Anwar Ur Rehman, "A Hybrid CNN-LSTM Model for Improving Accuracy of Movie Reviews Sentiment Analysis," Multimedia Tools and Applications, 2019. 

[64] "Amazon Customer Reviews Dataset," Amazon, [Online]. Available: https://s3.amazonaws.com/amazon-reviews-pds/readme.html.

[65] J. Berger, Statistical Decision Theory and Bayesian Analysis, New York, 1985. 

[66] D. M. W. Powers, "Evaluation: From Precision, Recall and F-Factor to ROC, Informedness, Markedness & Correlation," School of Informatics and Engineering, Australia, 2007.

[67] Bonett DG & RM Price, "Inferential Methods for the Tetrachoric Correlation Coefficient," Journal of Educational and Behavioral Statistics, vol. 30, no. 2, pp. 213-225, 2005. 

[68] C. J., "Assessing agreement on classification tasks: the kappa statistic," Computational Linguistics, vol. 22, no. 2, pp. 249-254, 1996. 

[69] C. J., "A coefficient of agreement for nominal scales," Educational and Psychological Measurement, pp. 37-46, 1960. 

[70] C. J., "Weighted kappa: Nominal scale agreement with provision for scaled disagreement or partial credit.," Psychological Bulletin, 1968. 

[71] J. M. A. &. P. F. Lafferty, "Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data. Proceedings of the 18th International Conference on Machine Learning," in Morgan Kaufmann, San Francisco, 2001. 

[72] Alimi, A. H. (2020). Deep learning CNN–LSTM framework for Arabic sentiment analysis using textual information shared in social networks. Social Network Analysis and Mining, 10(53).

[73] Pickard, T. (2020). Comparing word2vec and GloVe for Automatic Measurement of MWE Compositionality. Proceedings of the Joint Workshop on Multiword Expressions and Electronic Lexicons.