Product Review Ranking in e-Commerce using Urgency Level Classification Approach

Hamdi Ahmad Zuhri; Nur Ulfa Maulidevi

doi:10.15575/join.v5i2.612

Product Review Ranking in e-Commerce using Urgency Level Classification Approach

Hamdi Ahmad Zuhri, Nur Ulfa Maulidevi

Abstract

Review ranking is useful to give users a better experience. Review ranking studies commonly use upvote value, which does not represent urgency, and it causes problems in prediction. In contrast, manual labeling as wide as the upvote value range provides a high bias and inconsistency. The proposed solution is to use a classification approach to rank the review where the labels are ordinal urgency class. The experiment involved shallow learning models (Logistic Regression, Naïve Bayesian, Support Vector Machine, and Random Forest), and deep learning models (LSTM and CNN). In constructing a classification model, the problem is broken down into several binary classifications that predict tendencies of urgency depending on the separation of classes. The result shows that deep learning models outperform other models in classification dan ranking evaluation. In addition, the review data used tend to contain vocabulary of certain product domains, so further research is needed on data with more diverse vocabulary.

Keywords

Product review; Text classification; Text ranking

Full Text:

PDF

References

Chen, P.-Y., et al, "The impact of online recommendations and consumer feedback on sales". iCiS 2004 Proceedings, 2004.

Ghose, A., and Ipeirotis, P. G., "Designing a novel review ranking system: predicting the usefulness and impact of reviews," ACM, 2007, doi: https://doi.org/10.1145/1282100.1282158

He, Jiawei et al., "A Supervised Method for Ranking Reviews Based on Latent Structure Features," Proceedings of the 2016 IEEE International Conference on Knowledge Engineering and Applications, 2016, doi: https://doi.org/10.1109 /ICKEA.2016.7802998

Rajaraman, A. & Ullman, J.D., "Mining of Massive Datasets. Cambridge University Press, 2011," 2011, doi: https://doi.org/10.1017/CBO9781139058452

Burkov, Andriy, "The Hundred-Page Machine Learning," 2019.

Kleinbaum, David G., et al, "Logistic Regression, A Self-Learning Text," 2002.

Rish, Irina (2001), An Empirical Study of the Naïve Bayes Classifier. IJCAI workshop on Empirical Methods in AI.

El-Naqa, Issam, "A Support Vector Machine Approach for Detection of Microcalcifications," IEEE Trans. Med Imag., 2002, doi: https://doi.org/10.1109/TMI.2002.806569

Breiman, L., "Random Forests. Machine Learning," 2001.

Onan, Aytug, et al, "Ensemble of keyword extraction methods and classifiers in text classification," Expert Systems with Applications, vol. 57, 2016, doi: https://doi.org/10.1016/j.eswa.2016.03.045

Goodfellow, Ian, et al, "Deep Learning," 2016.

Sak, Hasim, et al, "Long Short-Term Memory Recurrent Neural Network Architectures for Large Scale Acoustic Modeling," Proceeding of Interspeech, 2014.

Chawla, N. V., et al, "SMOTE: Synthetic Minority Over-sampling Technique," Journal of artificial intelligence research, 16: 321-357, 2002, doi: https://doi.org/10.1613/jair.953

Olson, D. L., & Delen, D., "Advanced Data Mining Techniques," Springer Verlag, 2008.

Jarvelin, K., & Kekalainen, J., "Cumulated gain-based evaluation of IR techniques," ACM Transactions on Information Systems (TOIS), 2002, doi: https://doi.org/10.1145/582415.582418

Hsieh, Hsien-You & Wu, Shih-Hung, "Ranking Online Customer Reviews with the SVR Model", International Conference on Information Reuse and Integration, 2015

Saumya, Sunil, et al, "Ranking Online Consumer Reviews", Electronic Commerce Research and Applications,, 2018

Singh, J. P., et al, "Predicting the “helpfulness” of online consumer reviews", Journal of Business Reasearch, 2017