Analysis of Consumer Reviews by Machine Learning Techniques

  • Sourav SinhaEmail author
  • M. Sandhya
Conference paper
Part of the Lecture Notes on Data Engineering and Communications Technologies book series (LNDECT, volume 39)


The dynamic change in the usage of digital economy had drifted the customers towards using online shopping websites for their day to day purchase. Under such circumstances, customer reviews and ratings had been used by these online stores to generate trustworthy and esteemed brand in the digital market. Most of these reviews were unstructured text which had been widely used for sentiment analysis. This paper discusses about various machine learning algorithms proposed by different researchers to analyze the consumer reviews. Based on the existing work, we categorized three broad aspects in consumer reviews namely opinion mining, spam or fake review detection, collaborative filtering. In future work, we plan to propose customer review-oriented decision support system (CRDSS) which can help in consumer decision making process and thus improve the customer review helpfulness and rating prediction.


eCommerce Consumer review Sentiment analysis Machine learning 


  1. 1.
    Devasia, N., Sheik, R.: Feature extracted sentiment analysis of customer product reviews. In: International Conference on Emerging Technological Trends (ICETT), pp. 1–6. IEEE (2016)Google Scholar
  2. 2.
    Haque, T.U., Saber, M.N., Shah, F.M.: Sentimental analysis on large scale Amazon product reviews. In: International Conference on Innovative Research and Development, pp. 1–6. IEEE (2018)Google Scholar
  3. 3.
    Songpan, W.: The analysis of prediction of customer review rating using opinion mining. In: IEEE 15th International Conference on Software Engineering Research, Management and Applications (SERA), pp. 70–77 (2017)Google Scholar
  4. 4.
    Ejaz, A., Turabec, Z., Rashmi, M., Khoja, K.: Opinion mining approaches on Amazon product reviews a comparative study, pp. 173–179. IEEE (2017)Google Scholar
  5. 5.
    Zu, Q., Wu, J.: Big data analysis of reviews on e-commerce based on hadoop. In: HCC 2017. LNCS, vol. 10745, pp. 492–502. Springer (2018)Google Scholar
  6. 6.
    Fry, C., Manna, S.: Can we group similar Amazon reviews-a case study with different clustering algorithm. In: IEEE Tenth International Conference on Semantic Computer, pp. 324–329. IEEE (2016)Google Scholar
  7. 7.
    Hu, Z., Hu, J., Ding, W., Zheng, X.: Review sentimental analysis based on deep learning. In: IEEE 12th International Conference on e-business Engineering, pp. 87–94 (2015)Google Scholar
  8. 8.
    Khan, J., Jeong, B.S.: Summarizing customer review based on product feature and opinion. In: Proceedings of 2016 International Conference on Machine Learning and Cybernetics, pp. 158–165. IEEE (2016)Google Scholar
  9. 9.
    Wang, X., Lu, Z.: Extracting product features from online reviews based on two-level HHMM, pp. 1–4. IEEE (2014)Google Scholar
  10. 10.
    Ahsan, M.N.I., Nanian, T., Kofi, A.A., Hossain, M.I., Shah, F.M.: An ensemble approach to detect review spam using hybrid machine learning techniques. In: 19th International Conference on Computer and Information Technology, pp. 388–394. IEEE (2016)Google Scholar
  11. 11.
    Liu, P., Xu, Z., Ai, J., Wang, F.: Identifying indicators of fake reviews based on spammer’s behavior features. In: IEEE International Conference on Quality Reliability and Security (Companion Volume), pp. 396–403 (2017)Google Scholar
  12. 12.
    Zhang, L., Wu, Z., Cao, J.: Detecting spammer group from product reviews: a partially supervised learning model. IEEE Open Access J. 6, 2559–2568 (2012)CrossRefGoogle Scholar
  13. 13.
    Wang, H., Lue, L.: Collaborative filtering enhanced by user free text reviews topic modelling. In: International Conference on Information and Communications Technologies, pp. 1–5. IEEE (2014)Google Scholar
  14. 14.
    Wilson, J., Chaudhury, S., Lall, B.: Improving collaborative filtering based recommenders using topic modelling. In: IEEE/WIC/ACM International Joint Conference on Web Intelligence (WI) and Intelligent Agent Technologies (IAT), pp. 340–346 (2014)Google Scholar
  15. 15.
    Mahadevan, A., Arock, M.: Credible user review incorporated collaborative filtering for video recommendation system. In: Proceedings of ICISS 2017 IEEE Xplore Compliant, pp. 375–379. IEEE (2017)Google Scholar
  16. 16.
  17. 17.
  18. 18.
  19. 19.
    Lackermair, G., Kailar, D., Kanmaz, K.: Importance of online product reviews from a consumer prospective. Adv. Econ. Bus. 1(1), 1–5 (2013)Google Scholar
  20. 20.
    Manuel, T., Benedikt, B.: Analyzing online customer reviews – an interdisciplinary literature review and research agenda. In: Proceeding of the 21st European Conference on Information Systems, pp. 1–12 (2013)Google Scholar
  21. 21.
    Ahmad, T., Doja, M.N.: Opinion mining using frequent pattern growth method from unstructured text. In: International Symposium on Computational and Business Intelligence, pp. 92–95. IEEE (2013)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringB. S. Abdur Rahman Crescent Institute of Science and TechnologyChennaiIndia

Personalised recommendations